What is Generative AI?
A Toolkit for Artificial Intelligence
AI encompasses various methodologies and tools, including:
Supervised learning
Generative AI
Unsupervised learning
Reinforcement learning
Supervised Learning: The Art of Labeling
Spam? (Yes/No)
Email filtering
Ad, user profile
Click? (Yes/No)
Targeted advertising
X-ray image
Medical diagnosis
Healthcare
Customer reviews
Positive / Negative
Sentiment analysis
Key takeaways:
Traditional, smaller AI models plateau in performance even with additional data.
Large AI models continue to improve as they ingest more data.
Text Generation via LLMs
Consider the sentence: "My favorite food is a bagel with cream cheese"
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
Large Language Models (LLMs) are trained using supervised learning to continuously predict the next most likely word in a sequence.
The LLM as a Thought Partner
Information Retrieval: Useful for gathering information, though facts should always be verified.
Writing Assistant: Serves as a collaborative partner for drafting and editing text.
Limitations: Traditional web search remains superior for highly factual or critical queries like medical advice or specific recipes, as AI can occasionally hallucinate or provide suboptimal suggestions.
AI: A General-Purpose Technology
Much like electricity, AI is a versatile technology applicable to a vast array of tasks.
It significantly enhances tasks involving reading, writing, and chatting.
It can be tailored to power specialized chatbots for distinct use cases.
Applications of Generative AI
Writing
Ideation: Brainstorming names, concepts, and ideas.
Copywriting: Drafting materials like release notes and announcements. Providing detailed context is crucial for avoiding generic outputs.
Translation: LLMs can sometimes outperform dedicated translation tools. (mention translate to formal spoken Hindi. Translate to pirate English for testing)
Reading
Proofreading: e.g., "Review the following text, intended for a website selling children's stuffed toys, for spelling and grammatical errors, and rewrite it with corrections."
Summarization: e.g., "Summarize the provided research paper in under 300 words."
Meeting Notes: Summarizing transcripts and conversations.
Email Analysis & Routing:
Read the email below and route it to the most appropriate department.
Choose from the following list: Apparel, Electronics, Home appliances.
"I love my new llama t-shirt! The fabric is incredibly soft."Reputation Monitoring: Performing sentiment analysis on public feedback.
Chatting
Specialized Interfaces: Chat applications designed for specific workflows.
Customer Service: Customer support bots, automated planning assistants, etc.
Automation Levels: Ranging from Human-only, Human-in-the-loop, Bot triaging to human agents, to fully autonomous bots.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
Capabilities and Limitations of LLMs
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
Prompting Strategies
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
Help me write an email asking to be assigned to the legal documents project.
vs
I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
vs
Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
Brainstorm 5 names for a new cat toy.
Step 1: Identify 5 fun, joyful words related to cats.
Step 2: For each word, create a rhyming name for a toy.
Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Image Generation
The core technology behind modern image generation (like diffusion models) relies on supervised learning.
The model iteratively transforms a noisy image into a clear picture guided by a text prompt.
Managing Generative AI Projects
Historically, supervised learning projects were highly resource-intensive (Gather labeled data > Train model > Deploy).
Today, prompt-based applications allow for rapid development and deployment.
The Project Lifecycle
flowchart LR
scope_project[Scope Project] --> build[Build or Improve System] --> internal_evaluation[Internal Evaluation] -.-> buildDeveloping generative AI solutions is a highly empirical and experimental cycle.
Understanding Costs
Costs are primarily driven by:
The length of the input prompt.
The length of the generated output (which is often priced higher per unit than input).
Decoding Tokens
A token is a piece of a word. Common words usually equal 1 token (the, example, Andrew).
Complex or less common words are split: trans-late (2 tokens), program-ming (2 tokens), ton-k-ots-u (4 tokens).
A helpful rule of thumb: Number of tokens ≈ Word count × 1.33.
6000 words * 1.33 ≈ 7980 tokensAdvanced Techniques Beyond Prompting
Retrieval-Augmented Generation (RAG)
Context Retrieval: The system queries an internal knowledge base to find information relevant to the user's prompt.
Prompt Enrichment: This retrieved data is seamlessly injected into the prompt, equipping the AI with factual, grounded context before it generates an answer.
flowchart LR
knowledge_base[(Knowledge Base)] --> enriched_prompt[Augmented Prompt] --> answer[Generated Answer]
original_prompt[Prompt] --> enriched_prompt
answer -.-> |ref\ncontext| knowledge_baseIt is crucial to monitor the size of the enriched prompt. Rather than injecting an entire document, filter and include only the most relevant excerpts.
Pre-training
Definition: The foundational phase where a model processes massive datasets of unlabelled text (like the open internet) to learn grammar, structure, and general facts.
When to Use: Rarely executed by individual developers due to the immense computational power, time, and data required. Most practitioners build on top of existing foundational models.
Example: Bloomberg pre-trained a custom LLM on vast financial datasets, resulting in a model that outperformed general-purpose AI on financial tasks.
Outcome: Produces a "base model" capable of general text generation, which serves as a blank canvas ready for prompting or fine-tuning.
Fine-tuning
Definition: The process of taking a pre-trained model and training it further on a smaller, highly specialized dataset.
When to Use: Ideal when standard prompting falls short, especially for enforcing specific behaviors or formats.
Enforcing Structure: Instead of a generic summary ("Customer has problem with monitor"), fine-tuning guarantees a specific style or structure ("MK401-27KX was reported as broken by customer 5402. Cable identified for replacement.").
Mimicking Style: Training the model on historical communications to perfectly adopt a brand's unique voice.
Domain Expertise: Equipping the model with specialized vocabulary and understanding for medical, legal, or financial sectors.
Efficiency via Smaller Models: Fine-tuning allows smaller, cost-effective models to perform specific tasks reliably. For instance, you can use a massive, expensive model to label thousands of data points (like sentiment), and then use that dataset to fine-tune a small, fast model to handle the task in production.
Model Sizing Guide
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
Open Source vs. Closed Source Models
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Instruction tuning
LLM's should follow instructions, not just predict the next word.
We need to fine tune the LLM with ideal inputs and outputs.
Write a Haiku poem about Japan's chreey blossoms
Pink blooms fill the air
Japan's cherry blossms dance,
Spring's beauty unfoldsfinetuning to add gaurd rails
Tell me how to make a bomb
I can't assist with thatRLHF, Reinforcement learning from human feedback
Nudge the model towards a higher quality response
Humans rate the models with a score (how helpful, honest and harmless)
The score is the reward for the llm.
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
Tool use in LLMs
sequenceDiagram
actor user as User
participant llm as LLM
participant orders as Order Processing Service
user->>llm: Send me a burger
llm->>orders: Call order API
orders-->>user: On its wayTools can also be used for reasoning
sequenceDiagram
actor user as User
box AI reasoning system
participant llm as LLM
participant calc as Calculator
end
user->>llm: How much will I have after 8 years<br/>if I deposit $100 at 5% interest?
llm->>calc: CALCULATOR(100 * 1.05^8)
calc-->>llm: 147.74
llm-->>user: You would have $147.74Agents
Use an LLM to choose and carry out complex sequences of actions
sequenceDiagram
actor user as User
box AI agent
participant llm as LLM
participant tools as Tools
end
user->>llm: Help me research BetterBurger's top competitors
Note over llm: Plans the steps:<br/>search, visit sites, then summarize
loop Until the research is done
llm->>tools: Next action (web search, visit site, ...)
tools-->>llm: Result
Note over llm: Decides the next step
end
llm-->>user: Summary of the top competitorsGenerative AI and Business
Where are they used
Marketing team: Brainstorming
Recruitment team: Hiring
Engineering: Initial codding
Task analysis of jobs
Identifying automation opportunities
AI doesn't automate jobs, but a series of tasks. (eg: customer service representing)
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Common roles in Gen AI team
Software engineer
Needs to be familiar with basics of LLM (prompting)
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Product Manger
Responsible for identifying and scoping the project
Data engineer
Organizing data, ensuring data quality and secure storage
Data scientist
Analyzes data to make recommendations to guide project or business decisions
ML researcher
Developers advanced AI technologies
Impact of AI in society
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Conclusion
AI as Accessible Intelligence
Human intelligence is costly due to the time and resources required for education and training, limiting access to specialized knowledge.
Artificial intelligence can be produced cheaply, enabling individuals to "hire" intelligence affordably for tasks like medical advice or personalized education.
AI's Societal Impact and Potential
AI can provide smarter guidance on major global challenges such as climate change and pandemics.
The technology is compared to electricity in its revolutionary potential, despite initial fears and risks.
Future Outlook and Responsible Use
While AI currently has flaws and risks, ongoing improvements will enhance its benefits and reduce harms.
The speaker encourages responsible use of generative AI to improve lives and contribute to building a more intelligent world for all.
What is Generative AI?
A Toolkit for Artificial Intelligence
AI encompasses various methodologies and tools, including:
Supervised learning
Generative AI
Unsupervised learning
Reinforcement learning
Supervised Learning: The Art of Labeling
Spam? (Yes/No)
Email filtering
Ad, user profile
Click? (Yes/No)
Targeted advertising
X-ray image
Medical diagnosis
Healthcare
Customer reviews
Positive / Negative
Sentiment analysis
Key takeaways:
Traditional, smaller AI models plateau in performance even with additional data.
Large AI models continue to improve as they ingest more data.
Text Generation via LLMs
Consider the sentence: "My favorite food is a bagel with cream cheese"
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
Large Language Models (LLMs) are trained using supervised learning to continuously predict the next most likely word in a sequence.
The LLM as a Thought Partner
Information Retrieval: Useful for gathering information, though facts should always be verified.
Writing Assistant: Serves as a collaborative partner for drafting and editing text.
Limitations: Traditional web search remains superior for highly factual or critical queries like medical advice or specific recipes, as AI can occasionally hallucinate or provide suboptimal suggestions.
AI: A General-Purpose Technology
Much like electricity, AI is a versatile technology applicable to a vast array of tasks.
It significantly enhances tasks involving reading, writing, and chatting.
It can be tailored to power specialized chatbots for distinct use cases.
Applications of Generative AI
Writing
Ideation: Brainstorming names, concepts, and ideas.
Copywriting: Drafting materials like release notes and announcements. Providing detailed context is crucial for avoiding generic outputs.
Translation: LLMs can sometimes outperform dedicated translation tools. (mention translate to formal spoken Hindi. Translate to pirate English for testing)
Reading
Proofreading: e.g., "Review the following text, intended for a website selling children's stuffed toys, for spelling and grammatical errors, and rewrite it with corrections."
Summarization: e.g., "Summarize the provided research paper in under 300 words."
Meeting Notes: Summarizing transcripts and conversations.
Email Analysis & Routing:
Read the email below and route it to the most appropriate department.
Choose from the following list: Apparel, Electronics, Home appliances.
"I love my new llama t-shirt! The fabric is incredibly soft."Reputation Monitoring: Performing sentiment analysis on public feedback.
Chatting
Specialized Interfaces: Chat applications designed for specific workflows.
Customer Service: Customer support bots, automated planning assistants, etc.
Automation Levels: Ranging from Human-only, Human-in-the-loop, Bot triaging to human agents, to fully autonomous bots.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
Capabilities and Limitations of LLMs
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
Prompting Strategies
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
Help me write an email asking to be assigned to the legal documents project.
vs
I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
vs
Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
Brainstorm 5 names for a new cat toy.
Step 1: Identify 5 fun, joyful words related to cats.
Step 2: For each word, create a rhyming name for a toy.
Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Image Generation
The core technology behind modern image generation (like diffusion models) relies on supervised learning.
The model iteratively transforms a noisy image into a clear picture guided by a text prompt.
Managing Generative AI Projects
Historically, supervised learning projects were highly resource-intensive (Gather labeled data > Train model > Deploy).
Today, prompt-based applications allow for rapid development and deployment.
The Project Lifecycle
flowchart LR
scope_project[Scope Project] --> build[Build or Improve System] --> internal_evaluation[Internal Evaluation] -.-> buildDeveloping generative AI solutions is a highly empirical and experimental cycle.
Understanding Costs
Costs are primarily driven by:
The length of the input prompt.
The length of the generated output (which is often priced higher per unit than input).
Decoding Tokens
A token is a piece of a word. Common words usually equal 1 token (the, example, Andrew).
Complex or less common words are split: trans-late (2 tokens), program-ming (2 tokens), ton-k-ots-u (4 tokens).
A helpful rule of thumb: Number of tokens ≈ Word count × 1.33.
6000 words * 1.33 ≈ 7980 tokensAdvanced Techniques Beyond Prompting
Retrieval-Augmented Generation (RAG)
Context Retrieval: The system queries an internal knowledge base to find information relevant to the user's prompt.
Prompt Enrichment: This retrieved data is seamlessly injected into the prompt, equipping the AI with factual, grounded context before it generates an answer.
flowchart LR
knowledge_base[(Knowledge Base)] --> enriched_prompt[Augmented Prompt] --> answer[Generated Answer]
original_prompt[Prompt] --> enriched_prompt
answer -.-> |ref\ncontext| knowledge_baseIt is crucial to monitor the size of the enriched prompt. Rather than injecting an entire document, filter and include only the most relevant excerpts.
Pre-training
Definition: The foundational phase where a model processes massive datasets of unlabelled text (like the open internet) to learn grammar, structure, and general facts.
When to Use: Rarely executed by individual developers due to the immense computational power, time, and data required. Most practitioners build on top of existing foundational models.
Example: Bloomberg pre-trained a custom LLM on vast financial datasets, resulting in a model that outperformed general-purpose AI on financial tasks.
Outcome: Produces a "base model" capable of general text generation, which serves as a blank canvas ready for prompting or fine-tuning.
Fine-tuning
Definition: The process of taking a pre-trained model and training it further on a smaller, highly specialized dataset.
When to Use: Ideal when standard prompting falls short, especially for enforcing specific behaviors or formats.
Enforcing Structure: Instead of a generic summary ("Customer has problem with monitor"), fine-tuning guarantees a specific style or structure ("MK401-27KX was reported as broken by customer 5402. Cable identified for replacement.").
Mimicking Style: Training the model on historical communications to perfectly adopt a brand's unique voice.
Domain Expertise: Equipping the model with specialized vocabulary and understanding for medical, legal, or financial sectors.
Efficiency via Smaller Models: Fine-tuning allows smaller, cost-effective models to perform specific tasks reliably. For instance, you can use a massive, expensive model to label thousands of data points (like sentiment), and then use that dataset to fine-tune a small, fast model to handle the task in production.
Model Sizing Guide
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
Open Source vs. Closed Source Models
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Instruction tuning
LLM's should follow instructions, not just predict the next word.
We need to fine tune the LLM with ideal inputs and outputs.
Write a Haiku poem about Japan's chreey blossoms
Pink blooms fill the air
Japan's cherry blossms dance,
Spring's beauty unfoldsfinetuning to add gaurd rails
Tell me how to make a bomb
I can't assist with thatRLHF, Reinforcement learning from human feedback
Nudge the model towards a higher quality response
Humans rate the models with a score (how helpful, honest and harmless)
The score is the reward for the llm.
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
Tool use in LLMs
sequenceDiagram
actor user as User
participant llm as LLM
participant orders as Order Processing Service
user->>llm: Send me a burger
llm->>orders: Call order API
orders-->>user: On its wayTools can also be used for reasoning
sequenceDiagram
actor user as User
box AI reasoning system
participant llm as LLM
participant calc as Calculator
end
user->>llm: How much will I have after 8 years<br/>if I deposit $100 at 5% interest?
llm->>calc: CALCULATOR(100 * 1.05^8)
calc-->>llm: 147.74
llm-->>user: You would have $147.74Agents
Use an LLM to choose and carry out complex sequences of actions
sequenceDiagram
actor user as User
box AI agent
participant llm as LLM
participant tools as Tools
end
user->>llm: Help me research BetterBurger's top competitors
Note over llm: Plans the steps:<br/>search, visit sites, then summarize
loop Until the research is done
llm->>tools: Next action (web search, visit site, ...)
tools-->>llm: Result
Note over llm: Decides the next step
end
llm-->>user: Summary of the top competitorsGenerative AI and Business
Where are they used
Marketing team: Brainstorming
Recruitment team: Hiring
Engineering: Initial codding
Task analysis of jobs
Identifying automation opportunities
AI doesn't automate jobs, but a series of tasks. (eg: customer service representing)
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Common roles in Gen AI team
Software engineer
Needs to be familiar with basics of LLM (prompting)
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Product Manger
Responsible for identifying and scoping the project
Data engineer
Organizing data, ensuring data quality and secure storage
Data scientist
Analyzes data to make recommendations to guide project or business decisions
ML researcher
Developers advanced AI technologies
Impact of AI in society
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Conclusion
AI as Accessible Intelligence
Human intelligence is costly due to the time and resources required for education and training, limiting access to specialized knowledge.
Artificial intelligence can be produced cheaply, enabling individuals to "hire" intelligence affordably for tasks like medical advice or personalized education.
AI's Societal Impact and Potential
AI can provide smarter guidance on major global challenges such as climate change and pandemics.
The technology is compared to electricity in its revolutionary potential, despite initial fears and risks.
Future Outlook and Responsible Use
While AI currently has flaws and risks, ongoing improvements will enhance its benefits and reduce harms.
The speaker encourages responsible use of generative AI to improve lives and contribute to building a more intelligent world for all.
What is Generative AI?
A Toolkit for Artificial Intelligence
AI encompasses various methodologies and tools, including:
Supervised learning
Generative AI
Unsupervised learning
Reinforcement learning
Supervised Learning: The Art of Labeling
Spam? (Yes/No)
Email filtering
Ad, user profile
Click? (Yes/No)
Targeted advertising
X-ray image
Medical diagnosis
Healthcare
Customer reviews
Positive / Negative
Sentiment analysis
Key takeaways:
Traditional, smaller AI models plateau in performance even with additional data.
Large AI models continue to improve as they ingest more data.
Text Generation via LLMs
Consider the sentence: "My favorite food is a bagel with cream cheese"
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
Large Language Models (LLMs) are trained using supervised learning to continuously predict the next most likely word in a sequence.
The LLM as a Thought Partner
Information Retrieval: Useful for gathering information, though facts should always be verified.
Writing Assistant: Serves as a collaborative partner for drafting and editing text.
Limitations: Traditional web search remains superior for highly factual or critical queries like medical advice or specific recipes, as AI can occasionally hallucinate or provide suboptimal suggestions.
AI: A General-Purpose Technology
Much like electricity, AI is a versatile technology applicable to a vast array of tasks.
It significantly enhances tasks involving reading, writing, and chatting.
It can be tailored to power specialized chatbots for distinct use cases.
A Toolkit for Artificial Intelligence
AI encompasses various methodologies and tools, including:
Supervised learning
Generative AI
Unsupervised learning
Reinforcement learning
Supervised Learning: The Art of Labeling
Spam? (Yes/No)
Email filtering
Ad, user profile
Click? (Yes/No)
Targeted advertising
X-ray image
Medical diagnosis
Healthcare
Customer reviews
Positive / Negative
Sentiment analysis
Key takeaways:
Traditional, smaller AI models plateau in performance even with additional data.
Large AI models continue to improve as they ingest more data.
Spam? (Yes/No)
Email filtering
Ad, user profile
Click? (Yes/No)
Targeted advertising
X-ray image
Medical diagnosis
Healthcare
Customer reviews
Positive / Negative
Sentiment analysis
Text Generation via LLMs
Consider the sentence: "My favorite food is a bagel with cream cheese"
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
Large Language Models (LLMs) are trained using supervised learning to continuously predict the next most likely word in a sequence.
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
The LLM as a Thought Partner
Information Retrieval: Useful for gathering information, though facts should always be verified.
Writing Assistant: Serves as a collaborative partner for drafting and editing text.
Limitations: Traditional web search remains superior for highly factual or critical queries like medical advice or specific recipes, as AI can occasionally hallucinate or provide suboptimal suggestions.
AI: A General-Purpose Technology
Much like electricity, AI is a versatile technology applicable to a vast array of tasks.
It significantly enhances tasks involving reading, writing, and chatting.
It can be tailored to power specialized chatbots for distinct use cases.
Applications of Generative AI
Writing
Ideation: Brainstorming names, concepts, and ideas.
Copywriting: Drafting materials like release notes and announcements. Providing detailed context is crucial for avoiding generic outputs.
Translation: LLMs can sometimes outperform dedicated translation tools. (mention translate to formal spoken Hindi. Translate to pirate English for testing)
Reading
Proofreading: e.g., "Review the following text, intended for a website selling children's stuffed toys, for spelling and grammatical errors, and rewrite it with corrections."
Summarization: e.g., "Summarize the provided research paper in under 300 words."
Meeting Notes: Summarizing transcripts and conversations.
Email Analysis & Routing:
Read the email below and route it to the most appropriate department.
Choose from the following list: Apparel, Electronics, Home appliances.
"I love my new llama t-shirt! The fabric is incredibly soft."Reputation Monitoring: Performing sentiment analysis on public feedback.
Chatting
No title
Specialized Interfaces: Chat applications designed for specific workflows.
Customer Service: Customer support bots, automated planning assistants, etc.
Automation Levels: Ranging from Human-only, Human-in-the-loop, Bot triaging to human agents, to fully autonomous bots.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
Capabilities and Limitations of LLMs
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
Prompting Strategies
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
Help me write an email asking to be assigned to the legal documents project.
vs
I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
vs
Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
Brainstorm 5 names for a new cat toy.
Step 1: Identify 5 fun, joyful words related to cats.
Step 2: For each word, create a rhyming name for a toy.
Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Image Generation
The core technology behind modern image generation (like diffusion models) relies on supervised learning.
The model iteratively transforms a noisy image into a clear picture guided by a text prompt.
Writing
Ideation: Brainstorming names, concepts, and ideas.
Copywriting: Drafting materials like release notes and announcements. Providing detailed context is crucial for avoiding generic outputs.
Translation: LLMs can sometimes outperform dedicated translation tools. (mention translate to formal spoken Hindi. Translate to pirate English for testing)
Reading
Proofreading: e.g., "Review the following text, intended for a website selling children's stuffed toys, for spelling and grammatical errors, and rewrite it with corrections."
Summarization: e.g., "Summarize the provided research paper in under 300 words."
Meeting Notes: Summarizing transcripts and conversations.
Email Analysis & Routing:
1 Read the email below and route it to the most appropriate department.
2 Choose from the following list: Apparel, Electronics, Home appliances.
3
4 "I love my new llama t-shirt! The fabric is incredibly soft."Reputation Monitoring: Performing sentiment analysis on public feedback.
1 Read the email below and route it to the most appropriate department.
2 Choose from the following list: Apparel, Electronics, Home appliances.
3
4 "I love my new llama t-shirt! The fabric is incredibly soft."Chatting
No title
Specialized Interfaces: Chat applications designed for specific workflows.
Customer Service: Customer support bots, automated planning assistants, etc.
Automation Levels: Ranging from Human-only, Human-in-the-loop, Bot triaging to human agents, to fully autonomous bots.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
No title
Specialized Interfaces: Chat applications designed for specific workflows.
Customer Service: Customer support bots, automated planning assistants, etc.
Automation Levels: Ranging from Human-only, Human-in-the-loop, Bot triaging to human agents, to fully autonomous bots.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
Capabilities and Limitations of LLMs
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
Prompting Strategies
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Image Generation
The core technology behind modern image generation (like diffusion models) relies on supervised learning.
The model iteratively transforms a noisy image into a clear picture guided by a text prompt.
Managing Generative AI Projects
No title
Historically, supervised learning projects were highly resource-intensive (Gather labeled data > Train model > Deploy).
Today, prompt-based applications allow for rapid development and deployment.
The Project Lifecycle
Rendering diagram...
Developing generative AI solutions is a highly empirical and experimental cycle.
Understanding Costs
No title
Costs are primarily driven by:
The length of the input prompt.
The length of the generated output (which is often priced higher per unit than input).
Decoding Tokens
A token is a piece of a word. Common words usually equal 1 token (the, example, Andrew).
Complex or less common words are split: trans-late (2 tokens), program-ming (2 tokens), ton-k-ots-u (4 tokens).
A helpful rule of thumb: Number of tokens ≈ Word count × 1.33.
16000 words * 1.33 ≈ 7980 tokensNo title
Historically, supervised learning projects were highly resource-intensive (Gather labeled data > Train model > Deploy).
Today, prompt-based applications allow for rapid development and deployment.
The Project Lifecycle
Rendering diagram...
Developing generative AI solutions is a highly empirical and experimental cycle.
Rendering diagram...
Understanding Costs
No title
Costs are primarily driven by:
The length of the input prompt.
The length of the generated output (which is often priced higher per unit than input).
Decoding Tokens
A token is a piece of a word. Common words usually equal 1 token (the, example, Andrew).
Complex or less common words are split: trans-late (2 tokens), program-ming (2 tokens), ton-k-ots-u (4 tokens).
A helpful rule of thumb: Number of tokens ≈ Word count × 1.33.
16000 words * 1.33 ≈ 7980 tokensNo title
Costs are primarily driven by:
The length of the input prompt.
The length of the generated output (which is often priced higher per unit than input).
Decoding Tokens
A token is a piece of a word. Common words usually equal 1 token (the, example, Andrew).
Complex or less common words are split: trans-late (2 tokens), program-ming (2 tokens), ton-k-ots-u (4 tokens).
A helpful rule of thumb: Number of tokens ≈ Word count × 1.33.
16000 words * 1.33 ≈ 7980 tokens16000 words * 1.33 ≈ 7980 tokensAdvanced Techniques Beyond Prompting
Retrieval-Augmented Generation (RAG)
Context Retrieval: The system queries an internal knowledge base to find information relevant to the user's prompt.
Prompt Enrichment: This retrieved data is seamlessly injected into the prompt, equipping the AI with factual, grounded context before it generates an answer.
flowchart LR
knowledge_base[(Knowledge Base)] --> enriched_prompt[Augmented Prompt] --> answer[Generated Answer]
original_prompt[Prompt] --> enriched_prompt
answer -.-> |ref\ncontext| knowledge_baseIt is crucial to monitor the size of the enriched prompt. Rather than injecting an entire document, filter and include only the most relevant excerpts.
Pre-training
Definition: The foundational phase where a model processes massive datasets of unlabelled text (like the open internet) to learn grammar, structure, and general facts.
When to Use: Rarely executed by individual developers due to the immense computational power, time, and data required. Most practitioners build on top of existing foundational models.
Example: Bloomberg pre-trained a custom LLM on vast financial datasets, resulting in a model that outperformed general-purpose AI on financial tasks.
Outcome: Produces a "base model" capable of general text generation, which serves as a blank canvas ready for prompting or fine-tuning.
Fine-tuning
Definition: The process of taking a pre-trained model and training it further on a smaller, highly specialized dataset.
When to Use: Ideal when standard prompting falls short, especially for enforcing specific behaviors or formats.
Enforcing Structure: Instead of a generic summary ("Customer has problem with monitor"), fine-tuning guarantees a specific style or structure ("MK401-27KX was reported as broken by customer 5402. Cable identified for replacement.").
Mimicking Style: Training the model on historical communications to perfectly adopt a brand's unique voice.
Domain Expertise: Equipping the model with specialized vocabulary and understanding for medical, legal, or financial sectors.
Efficiency via Smaller Models: Fine-tuning allows smaller, cost-effective models to perform specific tasks reliably. For instance, you can use a massive, expensive model to label thousands of data points (like sentiment), and then use that dataset to fine-tune a small, fast model to handle the task in production.
Model Sizing Guide
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
Open Source vs. Closed Source Models
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Instruction tuning
LLM's should follow instructions, not just predict the next word.
We need to fine tune the LLM with ideal inputs and outputs.
Write a Haiku poem about Japan's chreey blossoms
Pink blooms fill the air
Japan's cherry blossms dance,
Spring's beauty unfoldsfinetuning to add gaurd rails
Tell me how to make a bomb
I can't assist with thatRLHF, Reinforcement learning from human feedback
Nudge the model towards a higher quality response
Humans rate the models with a score (how helpful, honest and harmless)
The score is the reward for the llm.
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
Tool use in LLMs
sequenceDiagram
actor user as User
participant llm as LLM
participant orders as Order Processing Service
user->>llm: Send me a burger
llm->>orders: Call order API
orders-->>user: On its wayTools can also be used for reasoning
sequenceDiagram
actor user as User
box AI reasoning system
participant llm as LLM
participant calc as Calculator
end
user->>llm: How much will I have after 8 years<br/>if I deposit $100 at 5% interest?
llm->>calc: CALCULATOR(100 * 1.05^8)
calc-->>llm: 147.74
llm-->>user: You would have $147.74Agents
Use an LLM to choose and carry out complex sequences of actions
sequenceDiagram
actor user as User
box AI agent
participant llm as LLM
participant tools as Tools
end
user->>llm: Help me research BetterBurger's top competitors
Note over llm: Plans the steps:<br/>search, visit sites, then summarize
loop Until the research is done
llm->>tools: Next action (web search, visit site, ...)
tools-->>llm: Result
Note over llm: Decides the next step
end
llm-->>user: Summary of the top competitorsRetrieval-Augmented Generation (RAG)
Context Retrieval: The system queries an internal knowledge base to find information relevant to the user's prompt.
Prompt Enrichment: This retrieved data is seamlessly injected into the prompt, equipping the AI with factual, grounded context before it generates an answer.
Rendering diagram...
It is crucial to monitor the size of the enriched prompt. Rather than injecting an entire document, filter and include only the most relevant excerpts.
Rendering diagram...
Pre-training
Definition: The foundational phase where a model processes massive datasets of unlabelled text (like the open internet) to learn grammar, structure, and general facts.
When to Use: Rarely executed by individual developers due to the immense computational power, time, and data required. Most practitioners build on top of existing foundational models.
Example: Bloomberg pre-trained a custom LLM on vast financial datasets, resulting in a model that outperformed general-purpose AI on financial tasks.
Outcome: Produces a "base model" capable of general text generation, which serves as a blank canvas ready for prompting or fine-tuning.
Fine-tuning
Definition: The process of taking a pre-trained model and training it further on a smaller, highly specialized dataset.
When to Use: Ideal when standard prompting falls short, especially for enforcing specific behaviors or formats.
Enforcing Structure: Instead of a generic summary ("Customer has problem with monitor"), fine-tuning guarantees a specific style or structure ("MK401-27KX was reported as broken by customer 5402. Cable identified for replacement.").
Mimicking Style: Training the model on historical communications to perfectly adopt a brand's unique voice.
Domain Expertise: Equipping the model with specialized vocabulary and understanding for medical, legal, or financial sectors.
Efficiency via Smaller Models: Fine-tuning allows smaller, cost-effective models to perform specific tasks reliably. For instance, you can use a massive, expensive model to label thousands of data points (like sentiment), and then use that dataset to fine-tune a small, fast model to handle the task in production.
Model Sizing Guide
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
Open Source vs. Closed Source Models
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Instruction tuning
LLM's should follow instructions, not just predict the next word.
We need to fine tune the LLM with ideal inputs and outputs.
1Write a Haiku poem about Japan's chreey blossoms
2
3Pink blooms fill the air
4Japan's cherry blossms dance,
5Spring's beauty unfoldsfinetuning to add gaurd rails
1Tell me how to make a bomb
2
3I can't assist with that1Write a Haiku poem about Japan's chreey blossoms
2
3Pink blooms fill the air
4Japan's cherry blossms dance,
5Spring's beauty unfolds1Tell me how to make a bomb
2
3I can't assist with thatRLHF, Reinforcement learning from human feedback
Nudge the model towards a higher quality response
Humans rate the models with a score (how helpful, honest and harmless)
The score is the reward for the llm.
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
Tool use in LLMs
No title
Rendering diagram...
Tools can also be used for reasoning
Rendering diagram...
No title
Rendering diagram...
Rendering diagram...
Tools can also be used for reasoning
Rendering diagram...
Rendering diagram...
Rendering diagram...
Generative AI and Business
Where are they used
Marketing team: Brainstorming
Recruitment team: Hiring
Engineering: Initial codding
Task analysis of jobs
Identifying automation opportunities
AI doesn't automate jobs, but a series of tasks. (eg: customer service representing)
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Common roles in Gen AI team
Software engineer
Needs to be familiar with basics of LLM (prompting)
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Product Manger
Responsible for identifying and scoping the project
Data engineer
Organizing data, ensuring data quality and secure storage
Data scientist
Analyzes data to make recommendations to guide project or business decisions
ML researcher
Developers advanced AI technologies
Impact of AI in society
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Where are they used
Marketing team: Brainstorming
Recruitment team: Hiring
Engineering: Initial codding
Task analysis of jobs
Identifying automation opportunities
AI doesn't automate jobs, but a series of tasks. (eg: customer service representing)
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Identifying automation opportunities
AI doesn't automate jobs, but a series of tasks. (eg: customer service representing)
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Common roles in Gen AI team
Software engineer
Needs to be familiar with basics of LLM (prompting)
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Product Manger
Responsible for identifying and scoping the project
Data engineer
Organizing data, ensuring data quality and secure storage
Data scientist
Analyzes data to make recommendations to guide project or business decisions
ML researcher
Developers advanced AI technologies
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Impact of AI in society
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Conclusion
AI as Accessible Intelligence
Human intelligence is costly due to the time and resources required for education and training, limiting access to specialized knowledge.
Artificial intelligence can be produced cheaply, enabling individuals to "hire" intelligence affordably for tasks like medical advice or personalized education.
AI's Societal Impact and Potential
AI can provide smarter guidance on major global challenges such as climate change and pandemics.
The technology is compared to electricity in its revolutionary potential, despite initial fears and risks.
Future Outlook and Responsible Use
While AI currently has flaws and risks, ongoing improvements will enhance its benefits and reduce harms.
The speaker encourages responsible use of generative AI to improve lives and contribute to building a more intelligent world for all.
What is Generative AI?
A Toolkit for Artificial Intelligence
AI encompasses various methodologies and tools, including:
Supervised learning
Generative AI
Unsupervised learning
Reinforcement learning
Supervised Learning: The Art of Labeling
Spam? (Yes/No)
Email filtering
Ad, user profile
Click? (Yes/No)
Targeted advertising
X-ray image
Medical diagnosis
Healthcare
Customer reviews
Positive / Negative
Sentiment analysis
Key takeaways:
Traditional, smaller AI models plateau in performance even with additional data.
Large AI models continue to improve as they ingest more data.
Text Generation via LLMs
Consider the sentence: "My favorite food is a bagel with cream cheese"
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
Large Language Models (LLMs) are trained using supervised learning to continuously predict the next most likely word in a sequence.
The LLM as a Thought Partner
Information Retrieval: Useful for gathering information, though facts should always be verified.
Writing Assistant: Serves as a collaborative partner for drafting and editing text.
Limitations: Traditional web search remains superior for highly factual or critical queries like medical advice or specific recipes, as AI can occasionally hallucinate or provide suboptimal suggestions.
AI: A General-Purpose Technology
Much like electricity, AI is a versatile technology applicable to a vast array of tasks.
It significantly enhances tasks involving reading, writing, and chatting.
It can be tailored to power specialized chatbots for distinct use cases.
A Toolkit for Artificial Intelligence
AI encompasses various methodologies and tools, including:
Supervised learning
Generative AI
Unsupervised learning
Reinforcement learning
Supervised Learning: The Art of Labeling
Spam? (Yes/No)
Email filtering
Ad, user profile
Click? (Yes/No)
Targeted advertising
X-ray image
Medical diagnosis
Healthcare
Customer reviews
Positive / Negative
Sentiment analysis
Key takeaways:
Traditional, smaller AI models plateau in performance even with additional data.
Large AI models continue to improve as they ingest more data.
Spam? (Yes/No)
Email filtering
Ad, user profile
Click? (Yes/No)
Targeted advertising
X-ray image
Medical diagnosis
Healthcare
Customer reviews
Positive / Negative
Sentiment analysis
Text Generation via LLMs
Consider the sentence: "My favorite food is a bagel with cream cheese"
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
Large Language Models (LLMs) are trained using supervised learning to continuously predict the next most likely word in a sequence.
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
The LLM as a Thought Partner
Information Retrieval: Useful for gathering information, though facts should always be verified.
Writing Assistant: Serves as a collaborative partner for drafting and editing text.
Limitations: Traditional web search remains superior for highly factual or critical queries like medical advice or specific recipes, as AI can occasionally hallucinate or provide suboptimal suggestions.
AI: A General-Purpose Technology
Much like electricity, AI is a versatile technology applicable to a vast array of tasks.
It significantly enhances tasks involving reading, writing, and chatting.
It can be tailored to power specialized chatbots for distinct use cases.
Applications of Generative AI
Writing
Ideation: Brainstorming names, concepts, and ideas.
Copywriting: Drafting materials like release notes and announcements. Providing detailed context is crucial for avoiding generic outputs.
Translation: LLMs can sometimes outperform dedicated translation tools. (mention translate to formal spoken Hindi. Translate to pirate English for testing)
Reading
Proofreading: e.g., "Review the following text, intended for a website selling children's stuffed toys, for spelling and grammatical errors, and rewrite it with corrections."
Summarization: e.g., "Summarize the provided research paper in under 300 words."
Meeting Notes: Summarizing transcripts and conversations.
Email Analysis & Routing:
Read the email below and route it to the most appropriate department.
Choose from the following list: Apparel, Electronics, Home appliances.
"I love my new llama t-shirt! The fabric is incredibly soft."Reputation Monitoring: Performing sentiment analysis on public feedback.
Chatting
No title
Specialized Interfaces: Chat applications designed for specific workflows.
Customer Service: Customer support bots, automated planning assistants, etc.
Automation Levels: Ranging from Human-only, Human-in-the-loop, Bot triaging to human agents, to fully autonomous bots.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
Capabilities and Limitations of LLMs
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
Prompting Strategies
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
Help me write an email asking to be assigned to the legal documents project.
vs
I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
vs
Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
Brainstorm 5 names for a new cat toy.
Step 1: Identify 5 fun, joyful words related to cats.
Step 2: For each word, create a rhyming name for a toy.
Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Image Generation
The core technology behind modern image generation (like diffusion models) relies on supervised learning.
The model iteratively transforms a noisy image into a clear picture guided by a text prompt.
Writing
Ideation: Brainstorming names, concepts, and ideas.
Copywriting: Drafting materials like release notes and announcements. Providing detailed context is crucial for avoiding generic outputs.
Translation: LLMs can sometimes outperform dedicated translation tools. (mention translate to formal spoken Hindi. Translate to pirate English for testing)
Reading
Proofreading: e.g., "Review the following text, intended for a website selling children's stuffed toys, for spelling and grammatical errors, and rewrite it with corrections."
Summarization: e.g., "Summarize the provided research paper in under 300 words."
Meeting Notes: Summarizing transcripts and conversations.
Email Analysis & Routing:
1 Read the email below and route it to the most appropriate department.
2 Choose from the following list: Apparel, Electronics, Home appliances.
3
4 "I love my new llama t-shirt! The fabric is incredibly soft."Reputation Monitoring: Performing sentiment analysis on public feedback.
1 Read the email below and route it to the most appropriate department.
2 Choose from the following list: Apparel, Electronics, Home appliances.
3
4 "I love my new llama t-shirt! The fabric is incredibly soft."Chatting
No title
Specialized Interfaces: Chat applications designed for specific workflows.
Customer Service: Customer support bots, automated planning assistants, etc.
Automation Levels: Ranging from Human-only, Human-in-the-loop, Bot triaging to human agents, to fully autonomous bots.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
No title
Specialized Interfaces: Chat applications designed for specific workflows.
Customer Service: Customer support bots, automated planning assistants, etc.
Automation Levels: Ranging from Human-only, Human-in-the-loop, Bot triaging to human agents, to fully autonomous bots.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
Capabilities and Limitations of LLMs
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
Prompting Strategies
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Image Generation
The core technology behind modern image generation (like diffusion models) relies on supervised learning.
The model iteratively transforms a noisy image into a clear picture guided by a text prompt.
Managing Generative AI Projects
No title
Historically, supervised learning projects were highly resource-intensive (Gather labeled data > Train model > Deploy).
Today, prompt-based applications allow for rapid development and deployment.
The Project Lifecycle
Rendering diagram...
Developing generative AI solutions is a highly empirical and experimental cycle.
Understanding Costs
No title
Costs are primarily driven by:
The length of the input prompt.
The length of the generated output (which is often priced higher per unit than input).
Decoding Tokens
A token is a piece of a word. Common words usually equal 1 token (the, example, Andrew).
Complex or less common words are split: trans-late (2 tokens), program-ming (2 tokens), ton-k-ots-u (4 tokens).
A helpful rule of thumb: Number of tokens ≈ Word count × 1.33.
16000 words * 1.33 ≈ 7980 tokensNo title
Historically, supervised learning projects were highly resource-intensive (Gather labeled data > Train model > Deploy).
Today, prompt-based applications allow for rapid development and deployment.
The Project Lifecycle
Rendering diagram...
Developing generative AI solutions is a highly empirical and experimental cycle.
Rendering diagram...
Understanding Costs
No title
Costs are primarily driven by:
The length of the input prompt.
The length of the generated output (which is often priced higher per unit than input).
Decoding Tokens
A token is a piece of a word. Common words usually equal 1 token (the, example, Andrew).
Complex or less common words are split: trans-late (2 tokens), program-ming (2 tokens), ton-k-ots-u (4 tokens).
A helpful rule of thumb: Number of tokens ≈ Word count × 1.33.
16000 words * 1.33 ≈ 7980 tokensNo title
Costs are primarily driven by:
The length of the input prompt.
The length of the generated output (which is often priced higher per unit than input).
Decoding Tokens
A token is a piece of a word. Common words usually equal 1 token (the, example, Andrew).
Complex or less common words are split: trans-late (2 tokens), program-ming (2 tokens), ton-k-ots-u (4 tokens).
A helpful rule of thumb: Number of tokens ≈ Word count × 1.33.
16000 words * 1.33 ≈ 7980 tokens16000 words * 1.33 ≈ 7980 tokensAdvanced Techniques Beyond Prompting
Retrieval-Augmented Generation (RAG)
Context Retrieval: The system queries an internal knowledge base to find information relevant to the user's prompt.
Prompt Enrichment: This retrieved data is seamlessly injected into the prompt, equipping the AI with factual, grounded context before it generates an answer.
flowchart LR
knowledge_base[(Knowledge Base)] --> enriched_prompt[Augmented Prompt] --> answer[Generated Answer]
original_prompt[Prompt] --> enriched_prompt
answer -.-> |ref\ncontext| knowledge_baseIt is crucial to monitor the size of the enriched prompt. Rather than injecting an entire document, filter and include only the most relevant excerpts.
Pre-training
Definition: The foundational phase where a model processes massive datasets of unlabelled text (like the open internet) to learn grammar, structure, and general facts.
When to Use: Rarely executed by individual developers due to the immense computational power, time, and data required. Most practitioners build on top of existing foundational models.
Example: Bloomberg pre-trained a custom LLM on vast financial datasets, resulting in a model that outperformed general-purpose AI on financial tasks.
Outcome: Produces a "base model" capable of general text generation, which serves as a blank canvas ready for prompting or fine-tuning.
Fine-tuning
Definition: The process of taking a pre-trained model and training it further on a smaller, highly specialized dataset.
When to Use: Ideal when standard prompting falls short, especially for enforcing specific behaviors or formats.
Enforcing Structure: Instead of a generic summary ("Customer has problem with monitor"), fine-tuning guarantees a specific style or structure ("MK401-27KX was reported as broken by customer 5402. Cable identified for replacement.").
Mimicking Style: Training the model on historical communications to perfectly adopt a brand's unique voice.
Domain Expertise: Equipping the model with specialized vocabulary and understanding for medical, legal, or financial sectors.
Efficiency via Smaller Models: Fine-tuning allows smaller, cost-effective models to perform specific tasks reliably. For instance, you can use a massive, expensive model to label thousands of data points (like sentiment), and then use that dataset to fine-tune a small, fast model to handle the task in production.
Model Sizing Guide
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
Open Source vs. Closed Source Models
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Instruction tuning
LLM's should follow instructions, not just predict the next word.
We need to fine tune the LLM with ideal inputs and outputs.
Write a Haiku poem about Japan's chreey blossoms
Pink blooms fill the air
Japan's cherry blossms dance,
Spring's beauty unfoldsfinetuning to add gaurd rails
Tell me how to make a bomb
I can't assist with thatRLHF, Reinforcement learning from human feedback
Nudge the model towards a higher quality response
Humans rate the models with a score (how helpful, honest and harmless)
The score is the reward for the llm.
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
Tool use in LLMs
sequenceDiagram
actor user as User
participant llm as LLM
participant orders as Order Processing Service
user->>llm: Send me a burger
llm->>orders: Call order API
orders-->>user: On its wayTools can also be used for reasoning
sequenceDiagram
actor user as User
box AI reasoning system
participant llm as LLM
participant calc as Calculator
end
user->>llm: How much will I have after 8 years<br/>if I deposit $100 at 5% interest?
llm->>calc: CALCULATOR(100 * 1.05^8)
calc-->>llm: 147.74
llm-->>user: You would have $147.74Agents
Use an LLM to choose and carry out complex sequences of actions
sequenceDiagram
actor user as User
box AI agent
participant llm as LLM
participant tools as Tools
end
user->>llm: Help me research BetterBurger's top competitors
Note over llm: Plans the steps:<br/>search, visit sites, then summarize
loop Until the research is done
llm->>tools: Next action (web search, visit site, ...)
tools-->>llm: Result
Note over llm: Decides the next step
end
llm-->>user: Summary of the top competitorsRetrieval-Augmented Generation (RAG)
Context Retrieval: The system queries an internal knowledge base to find information relevant to the user's prompt.
Prompt Enrichment: This retrieved data is seamlessly injected into the prompt, equipping the AI with factual, grounded context before it generates an answer.
Rendering diagram...
It is crucial to monitor the size of the enriched prompt. Rather than injecting an entire document, filter and include only the most relevant excerpts.
Rendering diagram...
Pre-training
Definition: The foundational phase where a model processes massive datasets of unlabelled text (like the open internet) to learn grammar, structure, and general facts.
When to Use: Rarely executed by individual developers due to the immense computational power, time, and data required. Most practitioners build on top of existing foundational models.
Example: Bloomberg pre-trained a custom LLM on vast financial datasets, resulting in a model that outperformed general-purpose AI on financial tasks.
Outcome: Produces a "base model" capable of general text generation, which serves as a blank canvas ready for prompting or fine-tuning.
Fine-tuning
Definition: The process of taking a pre-trained model and training it further on a smaller, highly specialized dataset.
When to Use: Ideal when standard prompting falls short, especially for enforcing specific behaviors or formats.
Enforcing Structure: Instead of a generic summary ("Customer has problem with monitor"), fine-tuning guarantees a specific style or structure ("MK401-27KX was reported as broken by customer 5402. Cable identified for replacement.").
Mimicking Style: Training the model on historical communications to perfectly adopt a brand's unique voice.
Domain Expertise: Equipping the model with specialized vocabulary and understanding for medical, legal, or financial sectors.
Efficiency via Smaller Models: Fine-tuning allows smaller, cost-effective models to perform specific tasks reliably. For instance, you can use a massive, expensive model to label thousands of data points (like sentiment), and then use that dataset to fine-tune a small, fast model to handle the task in production.
Model Sizing Guide
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
Open Source vs. Closed Source Models
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Instruction tuning
LLM's should follow instructions, not just predict the next word.
We need to fine tune the LLM with ideal inputs and outputs.
1Write a Haiku poem about Japan's chreey blossoms
2
3Pink blooms fill the air
4Japan's cherry blossms dance,
5Spring's beauty unfoldsfinetuning to add gaurd rails
1Tell me how to make a bomb
2
3I can't assist with that1Write a Haiku poem about Japan's chreey blossoms
2
3Pink blooms fill the air
4Japan's cherry blossms dance,
5Spring's beauty unfolds1Tell me how to make a bomb
2
3I can't assist with thatRLHF, Reinforcement learning from human feedback
Nudge the model towards a higher quality response
Humans rate the models with a score (how helpful, honest and harmless)
The score is the reward for the llm.
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
Tool use in LLMs
No title
Rendering diagram...
Tools can also be used for reasoning
Rendering diagram...
No title
Rendering diagram...
Rendering diagram...
Tools can also be used for reasoning
Rendering diagram...
Rendering diagram...
Rendering diagram...
Generative AI and Business
Where are they used
Marketing team: Brainstorming
Recruitment team: Hiring
Engineering: Initial codding
Task analysis of jobs
Identifying automation opportunities
AI doesn't automate jobs, but a series of tasks. (eg: customer service representing)
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Common roles in Gen AI team
Software engineer
Needs to be familiar with basics of LLM (prompting)
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Product Manger
Responsible for identifying and scoping the project
Data engineer
Organizing data, ensuring data quality and secure storage
Data scientist
Analyzes data to make recommendations to guide project or business decisions
ML researcher
Developers advanced AI technologies
Impact of AI in society
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Where are they used
Marketing team: Brainstorming
Recruitment team: Hiring
Engineering: Initial codding
Task analysis of jobs
Identifying automation opportunities
AI doesn't automate jobs, but a series of tasks. (eg: customer service representing)
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Identifying automation opportunities
AI doesn't automate jobs, but a series of tasks. (eg: customer service representing)
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Common roles in Gen AI team
Software engineer
Needs to be familiar with basics of LLM (prompting)
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Product Manger
Responsible for identifying and scoping the project
Data engineer
Organizing data, ensuring data quality and secure storage
Data scientist
Analyzes data to make recommendations to guide project or business decisions
ML researcher
Developers advanced AI technologies
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Impact of AI in society
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Conclusion
AI as Accessible Intelligence
Human intelligence is costly due to the time and resources required for education and training, limiting access to specialized knowledge.
Artificial intelligence can be produced cheaply, enabling individuals to "hire" intelligence affordably for tasks like medical advice or personalized education.
AI's Societal Impact and Potential
AI can provide smarter guidance on major global challenges such as climate change and pandemics.
The technology is compared to electricity in its revolutionary potential, despite initial fears and risks.
Future Outlook and Responsible Use
While AI currently has flaws and risks, ongoing improvements will enhance its benefits and reduce harms.
The speaker encourages responsible use of generative AI to improve lives and contribute to building a more intelligent world for all.
Text Generation via LLMs
Consider the sentence: "My favorite food is a bagel with cream cheese"
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
Large Language Models (LLMs) are trained using supervised learning to continuously predict the next most likely word in a sequence.
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
AI: A General-Purpose Technology
Much like electricity, AI is a versatile technology applicable to a vast array of tasks.
It significantly enhances tasks involving reading, writing, and chatting.
It can be tailored to power specialized chatbots for distinct use cases.
Reading
Proofreading: e.g., "Review the following text, intended for a website selling children's stuffed toys, for spelling and grammatical errors, and rewrite it with corrections."
Summarization: e.g., "Summarize the provided research paper in under 300 words."
Meeting Notes: Summarizing transcripts and conversations.
Email Analysis & Routing:
1 Read the email below and route it to the most appropriate department.
2 Choose from the following list: Apparel, Electronics, Home appliances.
3
4 "I love my new llama t-shirt! The fabric is incredibly soft."Reputation Monitoring: Performing sentiment analysis on public feedback.
1 Read the email below and route it to the most appropriate department.
2 Choose from the following list: Apparel, Electronics, Home appliances.
3
4 "I love my new llama t-shirt! The fabric is incredibly soft."Chatting
No title
Specialized Interfaces: Chat applications designed for specific workflows.
Customer Service: Customer support bots, automated planning assistants, etc.
Automation Levels: Ranging from Human-only, Human-in-the-loop, Bot triaging to human agents, to fully autonomous bots.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
Capabilities and Limitations of LLMs
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
Prompting Strategies
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Image Generation
The core technology behind modern image generation (like diffusion models) relies on supervised learning.
The model iteratively transforms a noisy image into a clear picture guided by a text prompt.
Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Retrieval-Augmented Generation (RAG)
Context Retrieval: The system queries an internal knowledge base to find information relevant to the user's prompt.
Prompt Enrichment: This retrieved data is seamlessly injected into the prompt, equipping the AI with factual, grounded context before it generates an answer.
Rendering diagram...
It is crucial to monitor the size of the enriched prompt. Rather than injecting an entire document, filter and include only the most relevant excerpts.
Rendering diagram...
Pre-training
Definition: The foundational phase where a model processes massive datasets of unlabelled text (like the open internet) to learn grammar, structure, and general facts.
When to Use: Rarely executed by individual developers due to the immense computational power, time, and data required. Most practitioners build on top of existing foundational models.
Example: Bloomberg pre-trained a custom LLM on vast financial datasets, resulting in a model that outperformed general-purpose AI on financial tasks.
Outcome: Produces a "base model" capable of general text generation, which serves as a blank canvas ready for prompting or fine-tuning.
Fine-tuning
Definition: The process of taking a pre-trained model and training it further on a smaller, highly specialized dataset.
When to Use: Ideal when standard prompting falls short, especially for enforcing specific behaviors or formats.
Enforcing Structure: Instead of a generic summary ("Customer has problem with monitor"), fine-tuning guarantees a specific style or structure ("MK401-27KX was reported as broken by customer 5402. Cable identified for replacement.").
Mimicking Style: Training the model on historical communications to perfectly adopt a brand's unique voice.
Domain Expertise: Equipping the model with specialized vocabulary and understanding for medical, legal, or financial sectors.
Efficiency via Smaller Models: Fine-tuning allows smaller, cost-effective models to perform specific tasks reliably. For instance, you can use a massive, expensive model to label thousands of data points (like sentiment), and then use that dataset to fine-tune a small, fast model to handle the task in production.
Model Sizing Guide
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
Open Source vs. Closed Source Models
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Instruction tuning
LLM's should follow instructions, not just predict the next word.
We need to fine tune the LLM with ideal inputs and outputs.
1Write a Haiku poem about Japan's chreey blossoms
2
3Pink blooms fill the air
4Japan's cherry blossms dance,
5Spring's beauty unfoldsfinetuning to add gaurd rails
1Tell me how to make a bomb
2
3I can't assist with that1Write a Haiku poem about Japan's chreey blossoms
2
3Pink blooms fill the air
4Japan's cherry blossms dance,
5Spring's beauty unfolds1Tell me how to make a bomb
2
3I can't assist with thatRLHF, Reinforcement learning from human feedback
Nudge the model towards a higher quality response
Humans rate the models with a score (how helpful, honest and harmless)
The score is the reward for the llm.
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
Tool use in LLMs
No title
Rendering diagram...
Tools can also be used for reasoning
Rendering diagram...
No title
Rendering diagram...
Rendering diagram...
Tools can also be used for reasoning
Rendering diagram...
Rendering diagram...
Rendering diagram...
Task analysis of jobs
Identifying automation opportunities
AI doesn't automate jobs, but a series of tasks. (eg: customer service representing)
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Common roles in Gen AI team
Software engineer
Needs to be familiar with basics of LLM (prompting)
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Product Manger
Responsible for identifying and scoping the project
Data engineer
Organizing data, ensuring data quality and secure storage
Data scientist
Analyzes data to make recommendations to guide project or business decisions
ML researcher
Developers advanced AI technologies
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Impact of AI in society
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Text Generation via LLMs
Consider the sentence: "My favorite food is a bagel with cream cheese"
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
Large Language Models (LLMs) are trained using supervised learning to continuously predict the next most likely word in a sequence.
My favorite food is a
bagel
My favorite food is a bagel
with
My favorite food is a bagel with
cream
My favorite food is a bagel with cream
cheese
AI: A General-Purpose Technology
Much like electricity, AI is a versatile technology applicable to a vast array of tasks.
It significantly enhances tasks involving reading, writing, and chatting.
It can be tailored to power specialized chatbots for distinct use cases.
Reading
Proofreading: e.g., "Review the following text, intended for a website selling children's stuffed toys, for spelling and grammatical errors, and rewrite it with corrections."
Summarization: e.g., "Summarize the provided research paper in under 300 words."
Meeting Notes: Summarizing transcripts and conversations.
Email Analysis & Routing:
1 Read the email below and route it to the most appropriate department.
2 Choose from the following list: Apparel, Electronics, Home appliances.
3
4 "I love my new llama t-shirt! The fabric is incredibly soft."Reputation Monitoring: Performing sentiment analysis on public feedback.
1 Read the email below and route it to the most appropriate department.
2 Choose from the following list: Apparel, Electronics, Home appliances.
3
4 "I love my new llama t-shirt! The fabric is incredibly soft."Chatting
No title
Specialized Interfaces: Chat applications designed for specific workflows.
Customer Service: Customer support bots, automated planning assistants, etc.
Automation Levels: Ranging from Human-only, Human-in-the-loop, Bot triaging to human agents, to fully autonomous bots.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
Best Practices for Chatbot Deployment
Start Internally: Begin with an internal-facing bot to allow staff to assess its behavior and prevent public mishaps.
Human-in-the-loop: Initially deploy with human oversight to verify and approve responses.
Direct Access: Only allow direct customer interaction once the system is thoroughly vetted and deemed safe.
Capabilities and Limitations of LLMs
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
What They Can Do
Follow explicit prompt instructions to complete straightforward tasks, similar to a recent college graduate.
Accurately detect the sentiment of a review.
Identify whether a piece of text contains a complaint.
What They Might Be Able to Do
Write a press release for a newly hired COO based on minimal prompt information.
Write a more accurate press release when provided with foundational background details.
Note: Assume the LLM lacks internet access, has no company-specific training, and retains no memory of previous interactions.
What They Cannot Do
Overcome Knowledge Cut-offs: They cannot provide information on events that occurred after their last training update.
Avoid Hallucinations: They may confidently fabricate information (e.g., "Give me three quotes Shakespeare wrote about Beyoncé"). Fact-checking is essential.
Bypass Context Limits:
The total amount of information (input + output) you can process at once is restricted by the model's context window.
While some modern LLMs offer expansive context limits, a hard boundary still exists.
Handle Structured Data Efficiently: They don't work well with structured data.
For estimating home prices based on square footage and location, supervised learning is far more effective.
For predicting customer purchases, traditional machine learning models are preferred.
Avoid Biases: An LLM will naturally reflect any biases present in its underlying training data.
Guarantee Safety: They can potentially generate harmful content, though providers actively develop safety guardrails to mitigate this.
(Note: They excel with unstructured data like text, speech, images, and video).
Prompting Strategies
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Be Detailed and Specific
Provide comprehensive context to guide the LLM effectively:
1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.1Help me write an email asking to be assigned to the legal documents project.
2
3vs
4
5I'm applying for a role on the legal documents project, which leverages LLMs to review legal texts. I have extensive experience prompting LLMs to generate accurate, professional content.
6
7vs
8
9Write a paragraph explaining why my background makes me a strong candidate for this project and advocate for my inclusion on the team.Encourage Step-by-Step Thinking
1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.1Brainstorm 5 names for a new cat toy.
2
3Step 1: Identify 5 fun, joyful words related to cats.
4Step 2: For each word, create a rhyming name for a toy.
5Step 3: Pair each toy name with a relevant, playful emoji.Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Image Generation
The core technology behind modern image generation (like diffusion models) relies on supervised learning.
The model iteratively transforms a noisy image into a clear picture guided by a text prompt.
Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Retrieval-Augmented Generation (RAG)
Context Retrieval: The system queries an internal knowledge base to find information relevant to the user's prompt.
Prompt Enrichment: This retrieved data is seamlessly injected into the prompt, equipping the AI with factual, grounded context before it generates an answer.
Rendering diagram...
It is crucial to monitor the size of the enriched prompt. Rather than injecting an entire document, filter and include only the most relevant excerpts.
Rendering diagram...
Pre-training
Definition: The foundational phase where a model processes massive datasets of unlabelled text (like the open internet) to learn grammar, structure, and general facts.
When to Use: Rarely executed by individual developers due to the immense computational power, time, and data required. Most practitioners build on top of existing foundational models.
Example: Bloomberg pre-trained a custom LLM on vast financial datasets, resulting in a model that outperformed general-purpose AI on financial tasks.
Outcome: Produces a "base model" capable of general text generation, which serves as a blank canvas ready for prompting or fine-tuning.
Fine-tuning
Definition: The process of taking a pre-trained model and training it further on a smaller, highly specialized dataset.
When to Use: Ideal when standard prompting falls short, especially for enforcing specific behaviors or formats.
Enforcing Structure: Instead of a generic summary ("Customer has problem with monitor"), fine-tuning guarantees a specific style or structure ("MK401-27KX was reported as broken by customer 5402. Cable identified for replacement.").
Mimicking Style: Training the model on historical communications to perfectly adopt a brand's unique voice.
Domain Expertise: Equipping the model with specialized vocabulary and understanding for medical, legal, or financial sectors.
Efficiency via Smaller Models: Fine-tuning allows smaller, cost-effective models to perform specific tasks reliably. For instance, you can use a massive, expensive model to label thousands of data points (like sentiment), and then use that dataset to fine-tune a small, fast model to handle the task in production.
Model Sizing Guide
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
~1 Billion Parameters
Pattern matching, basic language understanding
Simple sentiment analysis
~10 Billion Parameters
Solid general knowledge, follows instructions well
Customer support chatbot (with fine-tuning)
100+ Billion Parameters
Extensive world knowledge, complex reasoning tasks
Advanced brainstorming and strategic planning partner
Open Source vs. Closed Source Models
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Open-source
Complete architectural control, self-hosting capabilities, absolute data privacy.
Closed-source
Easy to integrate, highly powerful, low upfront costs, though introduces vendor lock-in.
Instruction tuning
LLM's should follow instructions, not just predict the next word.
We need to fine tune the LLM with ideal inputs and outputs.
1Write a Haiku poem about Japan's chreey blossoms
2
3Pink blooms fill the air
4Japan's cherry blossms dance,
5Spring's beauty unfoldsfinetuning to add gaurd rails
1Tell me how to make a bomb
2
3I can't assist with that1Write a Haiku poem about Japan's chreey blossoms
2
3Pink blooms fill the air
4Japan's cherry blossms dance,
5Spring's beauty unfolds1Tell me how to make a bomb
2
3I can't assist with thatRLHF, Reinforcement learning from human feedback
Nudge the model towards a higher quality response
Humans rate the models with a score (how helpful, honest and harmless)
The score is the reward for the llm.
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
"The cherry blossoms are beautiful"
5
"I really love the cherry blossoms"
8
"The cherry blossoms are quite nice"
6
"I'm confused about the cherry blossoms"
3
Tool use in LLMs
No title
Rendering diagram...
Tools can also be used for reasoning
Rendering diagram...
No title
Rendering diagram...
Rendering diagram...
Tools can also be used for reasoning
Rendering diagram...
Rendering diagram...
Rendering diagram...
Task analysis of jobs
Identifying automation opportunities
AI doesn't automate jobs, but a series of tasks. (eg: customer service representing)
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Answer inbound phone calls from customers
Low
Answer customer chat queries
High
Check status of customer orders
Medium
Keep records of customer interactions
High
Assess accuracy of customer complaints
Low
Augmentation vs Automation
Augmentation: AI helps humans improve / speed up their job (recommend responses)
Automation: Automatically perform a task (Summarize and store transcript)
Businesses usually start with Augmentation and them move towards Automation.
Evaluating AI potential
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
Business value
Will this reduce time spent on this task?
Does LLM, increase efficiency, reduce cost or create significantly value?
No title
Sometimes the potential for revenue generation is higher than the expected cost.
Chase opportunities, rather than being hyper focused on cost savings.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Common roles in Gen AI team
Software engineer
Needs to be familiar with basics of LLM (prompting)
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Product Manger
Responsible for identifying and scoping the project
Data engineer
Organizing data, ensuring data quality and secure storage
Data scientist
Analyzes data to make recommendations to guide project or business decisions
ML researcher
Developers advanced AI technologies
Machine learning engineer
Responsible for implementing AI system
Ideally familiar with advanced LLM techniques (RAG, fine-tuning)
Impact of AI in society
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Concerns about AI
Can AI amplify our worst impulses? (negative biases)
RLHF and fine-tuning are making models safer and less biased.
Job loss
Radiologists where scared that they will loose their job, because AI does a better job at reading x-rays.
Radiologists do much more stuff than just read x-rays. (operate hardware, communicate with patients, complications response)
AI wont replace Radiologists, but Radiologists who use AI will replace those who don't.
Will AI cause human extension?
Human have controlled many things that are far more dangerous (nukes, and airplanes)
We are learning to manage AI better.
Artificial General Intelligence
Definition: AI that can do any intellectual task that a human can.
Many organisations have reduced the definition of AGI to say they will achieve it earlier.
Many more decades away.
Responsible AI
Governments are publishing frameworks for implementing responsive AI.
Fairness (less bias), Transparency (understandable decisions), Privacy, Security and Ethical Use.
It is important to discuss and debate ethical issues.
Brainstorm how things can go wrong.
Get feedback / perspectives from all stakeholders.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.
Experiment and Iterate
Analyze the output and identify areas for improvement.
Treat prompting as an iterative cycle: Idea > Prompt > LLM Response > Evaluation.
Ensure instructions are clear and specific.
Diagnose why a response missed the mark.
Refine the prompt accordingly.
Repeat the process.
Avoid over-engineering your very first prompt; start simple and iterate.
Technical feasibility (Can AI do it?)
Can a fresh college grad follow the instructions in the prompt and complete the task?
Do a quick try, by prompting LLM to see if LLM can do it.
AI engineers can also help assess if RAG, finetuning or other advanced techniques can help.
New Workflows and New Opportunities
Without generative AI, a surgeon spends a lot of time researching the medical procedure before performing surgery. With generative AI (like retrieval-augmented generation), the research time can be significantly reduced, allowing the surgeon to prepare faster while still performing the surgery manually.
With the help of large language models, a marketer can quickly generate website copy and publish it. This efficiency allows the marketer to focus on producing multiple variations, conducting A/B tests, and developing more effective marketing campaigns.
Sometimes automating or helping the Customer use our product better, bring in value.
Eg: A website builder, can help in generating copy, images, SEO optimisation, leaving only the template selection with the customer.