際際滷

際際滷Share a Scribd company logo

ITB 2023 - Chatgpt Box! AI All The Things - Scott Steinbeck.pdf

Ortus Solutions, Corp
Ortus Solutions, Corp

Ortus and the CFML Community have developed ChatGPT Box in response to the AI explosion. This session explores ChatGPT Box's purpose, problem-solving capabilities, and the reasoning behind using AI. It covers the training process and underlying science. The talk highlights how ChatGPT Box 1.0.0 is just the beginning, discussing future possibilities and how it can boost productivity for Ortusian Developers. The presentation aims to demonstrate the practical value of AI for developers and businesses.

1 of 40
Download to read offline
Session ChatGPT Box LED BY SCOTT STEINBECK
SCOTT STEINBECK SPEAKER AT ITB2023 Software Engineer 15+ Year of experience Father Hardware Tinkerer Coding on my free time Overcommitting myself Automating everything IOT Development Teaching Coding/Electronics Contributing to open source Hobbies
BREIF HISTORY Thanks to our sponsors
Traditional language models (e.g., n-gram models) had limitations: Explosion of state space (curse of dimensionality) and sparsity led to inconsistent output resembling gibberish. Inability to handle novel phrases and lack of coherence in the generated text. Pre-2000's:
Advancements in training neural networks by Geo鍖rey Hinton: Deep neural networks alleviated some language model problems. Nuanced arbitrary concepts were represented in a 鍖nite space, but output lacked coherence relative to the input sequence. Mid-2000's:
Rise of Long Short-Term Memory (LSTM) networks: LSTMs enabled processing of arbitrary length sequences. Dynamic alteration of internal state improved language model performance signi鍖cantly. Early-2010's:
Introduction of Transformer Networks with the "Attention Is All You Need" paper by Google: Transformers revolutionized natural language processing, achieving tasks like language translation at human-level or better. Attention mechanisms and parallel processing allowed the model to analyze the entire input simultaneously. Late-2010's:
Emergence of Generative Pre-Trained (GPT) models, notably GPT-3: Large language models could be trained on massive data without speci鍖c agendas. Fine-tuning for speci鍖c tasks led to state-of-the-art results via text interaction. 2020's 1 petabyte of training data
DIGGING IN Thanks to our sponsors
AI UNDER THE HOOD AI, or Artificial Intelligence, is a broad field that encompasses the development of intelligent systems capable of performing tasks that typically require human intelligence. This works by combining rule-based modeling of human languagewith statistical, machine learning, and deep learning models
Natural Language Processing Tasks Natural Language Understanding (NLU) deals with the ability of computers to understand human language. Natural Language Generation (NLG) data to text - text is generated to explain or describe a structured record or unstructured perceptual input; text to text - typically involves fusing information from multiple linguistic sources into a single coherent summary; dialogue - text is generated as part of an interactive conversation with one or more human participants.
Machine Learning ML techniques play a key role in AI by enabling systems to automatically learn from experience, adapt to new data, and improve their performance over time. ML algorithms are used in various AI applications, including computer vision, speech recognition, recommendation systems, and, importantly, NLP tasks. Machine Learning to Play Hill Climb Racing
Deep Learning DL has revolutionized ML by enabling models to automatically learn more abstract and nuanced features from raw data. DL help NLP to understand natural language, enabling them to capture contextual dependencies and learn complex representations. Deep Learning to car attribute classification
WHAT IS AN LLM Practical AI A large language model is a prediction engine that takes a sequence of words and tries to predict the most likely sequence to come after that sequence. It does this by assigning a probability to likely next sequences and then samples from those to choose one. The process repeats until some stopping criteria is met. APPLICATIONS AND INFRASTRUCTURE USING ARTIFICIAL INTELLIGENCE TODAY
HOW AI LEARNS NEW ABILITIES Practical AI As LLMs are scaled they hit a series of critical scales at which new abilities are suddenly unlocked. LLMs are not directly trained to have these abilities, and they appear in rapid and unpredictable ways as if emerging out of thin air.
Applications of Large Language Models Practical AI
ASKING AI A QUESTION Thanks to our sponsors
TOKENIZATION CHATGPT What are some common mistakes to avoid when writing code? Tokens can be words, subwords, or characters, depending on the specific tokenization scheme used.
INPUT ANALYSIS CHATGPT 1. Informational Questions: "What is the capital of France?" "Can you explain the concept of relativity?" 2. Procedural Questions: "What are the steps to install a software program?" 3. Comparison Questions: "Compare the advantages of iOS and Android." 4. Opinion Questions: Do you think technology is making us more connected or disconnected?" 5. Problem-Solving Questions: "How can I optimize my website's loading speed?" 6. Request for Advice: "Which programming language should I learn as a beginner?" 7. Request for Explanation: "What is the significance of the Pythagorean theorem?" What are some common mistakes to avoid when writing code?
Understanding the Question CHATGPT 1. Neural Networks turn tokens into dense vectors (word embeddings) This adds context and captures complex relationships between words What are some common mistakes to avoid when writing code? Vectors with shorter distances between them usually share common contexts in the corpus. This allows us to find distances between words |cat - dog| = 1.20 |cat - cow| = 1.48 "cat" is closer to "dog" than it is to the "cow". Monday Vector What Vector
Retrieval/Integration of Knowledge CHATGPT _ _ _ _ mistakes _ avoid _ writing code?
Generating the Answer CHATGPT _ _ _ _ mistakes _ avoid _ writing code? Common mistakes to avoid when writing code include: Poor code organization and lack of proper indentation. Inefficient algorithms or data structures that result in slow performance. Lack of proper error handling and exception management. Insufficient comments and documentation, making the code difficult to understand and maintain. Failure to validate input data, leading to potential security vulnerabilities. Hardcoding values instead of using constants or configuration files. Ignoring code style conventions, making the codebase inconsistent and harder to read. Neglecting to handle edge cases and unexpected scenarios. Not using version control, resulting in difficulties in tracking changes and collaborating with others. Overcomplicating solutions instead of keeping the code simple and maintainable.
PROMPT ENGINEERING Thanks to our sponsors
WHAT IS A PROMPT CHATGPT A prompt, sometimes referred to as context, is the text provided to a model before it begins generating output. It guides the model to explore a particular area of what it has learned so that the output is relevant to your goals. Prompts are the secret sauce of chat agents
MORE DETAILED PROMPTS CHATGPT Responses are only as detailed as focused as the question that is asked. You can see we explain to the bot the various roles we get a more concise answer: Give the bot a role Give some context on the user Give some dynamic data we want the bot to have access to and then guidance on how the bot should respond. CHAT GPT IS EXCEPTIONALLY GOOD AT UNDERSTANDING MARKDOWN & JSON
GIVING CHATGPT JSON AND ASKING QUESTIONS CHATGPT
CRAFTING YOUR OWN PROMPTS CHATGPT if you were helping a user book a trip, you could: Ask the user their dates and destination. Behind the scenes, search for flights and hotels. Embed the flight and hotel search results in the hidden context. Also embed the companys travel policy in the hidden context.
CONTEXT PROMPTING https://prompts.chat/ CHATGPT
ONE SHOT PROMPTING CHATGPT These types of prompts provide the AI model with one example of what you expect the output to be. The basic steps are: Give a quick explanation of what you need, add a question-answer pair or a template as an example
FEW SHOT PROMPTING CHATGPT Large language models are few-shot learners, meaning that they can learn a new task by being provided just a few examples. The basic steps are: Give a quick explanation of what you need, add a few question-answer pairs or templates as an example.
FEW SHOT PROMPTING CHATGPT Large language models are few-shot learners, meaning that they can learn a new task by being provided just a few examples. The basic steps are: Give a quick explanation of what you need, add a few question-answer pairs or templates as an example.
CHAIN OF THOUGHT PROMPTING CHATGPT
AUGMENTING LARGE LANGUAGE MODELS Thanks to our sponsors
EXPANDING LLM FUNCTIONALITY CHATGPT
PROMPT TEMPLATES CHATGPT
DOCUMENT LOADERS CHATGPT
VECTOR DATABASES CHATGPT Full-text search VS Semantic search
AGENTS CHATGPT Build your own chat that pulls in other services attach calculator tool for questions regarding calculations
TOOLS/UTILS CHATGPT https://muze.one/ https://www.dailybot.com/
CHATGPT THANK YOU

More Related Content

ITB 2023 - Chatgpt Box! AI All The Things - Scott Steinbeck.pdf

  • 2. SCOTT STEINBECK SPEAKER AT ITB2023 Software Engineer 15+ Year of experience Father Hardware Tinkerer Coding on my free time Overcommitting myself Automating everything IOT Development Teaching Coding/Electronics Contributing to open source Hobbies
  • 3. BREIF HISTORY Thanks to our sponsors
  • 4. Traditional language models (e.g., n-gram models) had limitations: Explosion of state space (curse of dimensionality) and sparsity led to inconsistent output resembling gibberish. Inability to handle novel phrases and lack of coherence in the generated text. Pre-2000's:
  • 5. Advancements in training neural networks by Geo鍖rey Hinton: Deep neural networks alleviated some language model problems. Nuanced arbitrary concepts were represented in a 鍖nite space, but output lacked coherence relative to the input sequence. Mid-2000's:
  • 6. Rise of Long Short-Term Memory (LSTM) networks: LSTMs enabled processing of arbitrary length sequences. Dynamic alteration of internal state improved language model performance signi鍖cantly. Early-2010's:
  • 7. Introduction of Transformer Networks with the "Attention Is All You Need" paper by Google: Transformers revolutionized natural language processing, achieving tasks like language translation at human-level or better. Attention mechanisms and parallel processing allowed the model to analyze the entire input simultaneously. Late-2010's:
  • 8. Emergence of Generative Pre-Trained (GPT) models, notably GPT-3: Large language models could be trained on massive data without speci鍖c agendas. Fine-tuning for speci鍖c tasks led to state-of-the-art results via text interaction. 2020's 1 petabyte of training data
  • 9. DIGGING IN Thanks to our sponsors
  • 10. AI UNDER THE HOOD AI, or Artificial Intelligence, is a broad field that encompasses the development of intelligent systems capable of performing tasks that typically require human intelligence. This works by combining rule-based modeling of human languagewith statistical, machine learning, and deep learning models
  • 11. Natural Language Processing Tasks Natural Language Understanding (NLU) deals with the ability of computers to understand human language. Natural Language Generation (NLG) data to text - text is generated to explain or describe a structured record or unstructured perceptual input; text to text - typically involves fusing information from multiple linguistic sources into a single coherent summary; dialogue - text is generated as part of an interactive conversation with one or more human participants.
  • 12. Machine Learning ML techniques play a key role in AI by enabling systems to automatically learn from experience, adapt to new data, and improve their performance over time. ML algorithms are used in various AI applications, including computer vision, speech recognition, recommendation systems, and, importantly, NLP tasks. Machine Learning to Play Hill Climb Racing
  • 13. Deep Learning DL has revolutionized ML by enabling models to automatically learn more abstract and nuanced features from raw data. DL help NLP to understand natural language, enabling them to capture contextual dependencies and learn complex representations. Deep Learning to car attribute classification
  • 14. WHAT IS AN LLM Practical AI A large language model is a prediction engine that takes a sequence of words and tries to predict the most likely sequence to come after that sequence. It does this by assigning a probability to likely next sequences and then samples from those to choose one. The process repeats until some stopping criteria is met. APPLICATIONS AND INFRASTRUCTURE USING ARTIFICIAL INTELLIGENCE TODAY
  • 15. HOW AI LEARNS NEW ABILITIES Practical AI As LLMs are scaled they hit a series of critical scales at which new abilities are suddenly unlocked. LLMs are not directly trained to have these abilities, and they appear in rapid and unpredictable ways as if emerging out of thin air.
  • 16. Applications of Large Language Models Practical AI
  • 17. ASKING AI A QUESTION Thanks to our sponsors
  • 18. TOKENIZATION CHATGPT What are some common mistakes to avoid when writing code? Tokens can be words, subwords, or characters, depending on the specific tokenization scheme used.
  • 19. INPUT ANALYSIS CHATGPT 1. Informational Questions: "What is the capital of France?" "Can you explain the concept of relativity?" 2. Procedural Questions: "What are the steps to install a software program?" 3. Comparison Questions: "Compare the advantages of iOS and Android." 4. Opinion Questions: Do you think technology is making us more connected or disconnected?" 5. Problem-Solving Questions: "How can I optimize my website's loading speed?" 6. Request for Advice: "Which programming language should I learn as a beginner?" 7. Request for Explanation: "What is the significance of the Pythagorean theorem?" What are some common mistakes to avoid when writing code?
  • 20. Understanding the Question CHATGPT 1. Neural Networks turn tokens into dense vectors (word embeddings) This adds context and captures complex relationships between words What are some common mistakes to avoid when writing code? Vectors with shorter distances between them usually share common contexts in the corpus. This allows us to find distances between words |cat - dog| = 1.20 |cat - cow| = 1.48 "cat" is closer to "dog" than it is to the "cow". Monday Vector What Vector
  • 21. Retrieval/Integration of Knowledge CHATGPT _ _ _ _ mistakes _ avoid _ writing code?
  • 22. Generating the Answer CHATGPT _ _ _ _ mistakes _ avoid _ writing code? Common mistakes to avoid when writing code include: Poor code organization and lack of proper indentation. Inefficient algorithms or data structures that result in slow performance. Lack of proper error handling and exception management. Insufficient comments and documentation, making the code difficult to understand and maintain. Failure to validate input data, leading to potential security vulnerabilities. Hardcoding values instead of using constants or configuration files. Ignoring code style conventions, making the codebase inconsistent and harder to read. Neglecting to handle edge cases and unexpected scenarios. Not using version control, resulting in difficulties in tracking changes and collaborating with others. Overcomplicating solutions instead of keeping the code simple and maintainable.
  • 24. WHAT IS A PROMPT CHATGPT A prompt, sometimes referred to as context, is the text provided to a model before it begins generating output. It guides the model to explore a particular area of what it has learned so that the output is relevant to your goals. Prompts are the secret sauce of chat agents
  • 25. MORE DETAILED PROMPTS CHATGPT Responses are only as detailed as focused as the question that is asked. You can see we explain to the bot the various roles we get a more concise answer: Give the bot a role Give some context on the user Give some dynamic data we want the bot to have access to and then guidance on how the bot should respond. CHAT GPT IS EXCEPTIONALLY GOOD AT UNDERSTANDING MARKDOWN & JSON
  • 26. GIVING CHATGPT JSON AND ASKING QUESTIONS CHATGPT
  • 27. CRAFTING YOUR OWN PROMPTS CHATGPT if you were helping a user book a trip, you could: Ask the user their dates and destination. Behind the scenes, search for flights and hotels. Embed the flight and hotel search results in the hidden context. Also embed the companys travel policy in the hidden context.
  • 29. ONE SHOT PROMPTING CHATGPT These types of prompts provide the AI model with one example of what you expect the output to be. The basic steps are: Give a quick explanation of what you need, add a question-answer pair or a template as an example
  • 30. FEW SHOT PROMPTING CHATGPT Large language models are few-shot learners, meaning that they can learn a new task by being provided just a few examples. The basic steps are: Give a quick explanation of what you need, add a few question-answer pairs or templates as an example.
  • 31. FEW SHOT PROMPTING CHATGPT Large language models are few-shot learners, meaning that they can learn a new task by being provided just a few examples. The basic steps are: Give a quick explanation of what you need, add a few question-answer pairs or templates as an example.
  • 32. CHAIN OF THOUGHT PROMPTING CHATGPT
  • 38. AGENTS CHATGPT Build your own chat that pulls in other services attach calculator tool for questions regarding calculations