A Primer on AI for Architects with Anthony Alford

Machine Learning Concepts

• Architects need to understand AI and machine learning concepts to have intelligent conversations with their co-workers. (2m30s)
• Most people are referring to machine learning, specifically deep learning or neural networks, when they talk about AI. (3m21s)

Machine Learning Models

• Software developers can think of machine learning models as functions that take complex inputs, such as images or audio, and produce complex outputs, such as transcripts or summaries. (4m20s)
• Tensors are multi-dimensional arrays used in machine learning models. (5m57s)
• Machine learning models are trained using a process called supervised learning, which involves providing the model with inputs and expected outputs, similar to unit tests in software development. (6m15s)

Language Models

• Language models, such as ChatGPT, are trained on vast amounts of text data to predict the probability of a word occurring next in a sequence. (8m39s)
• Large language models (LLMs) are characterized by having tens or hundreds of billions of parameters. (12m42s)
• Hugging Face is a platform similar to GitHub, hosting and providing access to LLMs, including smaller models that can run on personal laptops. (13m39s)
• LLMs utilize "tokens," which are units of text smaller than words, allowing them to generate novel words and phrases not found in a standard vocabulary. (17m2s)
• Tokenization is a process that breaks down text into smaller units, typically larger than a character but smaller than a word. (17m54s)
• Large language models (LLMs) like ChatGPT and OpenAI's API use tokens to measure usage and billing. (18m9s)
• The "T" in GPT stands for Transformer, a neural network architecture that utilizes an "attention" mechanism to process and generate text. (20m59s)

Large Language Model Access

• There are publicly available, commercial large language models (LLMs) such as GPT-4, ChatGPT, Claude, Google's Gemini, and offerings from AWS. These can be accessed through web-based APIs and integrated using SDKs. (23m56s)
• While using commercial LLMs can be cost-effective in the short term due to a pay-per-token model, long-term cost and privacy concerns may arise. (24m34s)
• Open-source LLMs offer an alternative to commercial options, allowing for in-house implementation and greater control over data privacy. (25m19s)

Large Language Model Characteristics

• Large language models (LLMs) are non-deterministic, meaning the output for a given input is not always predictable. (29m5s)

Retrieval Augmented Generation (RAG)

• Retrieval augmented generation (RAG) is a technique that can improve the quality of LLM results by providing the model with relevant context from a knowledge base. (30m38s)
• RAG works by converting documents and user queries into vectors, then finding the closest matching vectors to provide context to the LLM. (32m0s)

Transfer Learning and Fine-tuning

• Transfer learning is a machine learning technique used to pre-train a model for general purposes and then fine-tune it for specific tasks. (34m37s)
• Fine-tuning involves restarting the training process with a smaller dataset specific to the desired outcome, allowing for adjustments to the model's responses. (35m1s)

Vector Databases

• Vector databases, often used in semantic or neural search, employ nearest neighbor search algorithms to efficiently find vectors similar to a given input vector, enabling the retrieval of related content based on meaning. (38m9s)

Large Language Model Applications

• LLMs can be understood as tools for addressing natural language processing tasks, such as named entity recognition and parts of speech recognition. (40m6s)
• LLMs are versatile and can be fine-tuned for specific use cases or chosen based on their proximity to a desired application, offering advantages in cost, quality, and speed. (40m50s)

AI Co-pilots and AI Agents

• A distinction is made between AI co-pilots, which require user initiation, and AI agents, which possess a degree of autonomy. (43m8s)