ai-notes

Maintains a structured, continuously-updated knowledge base documenting the evolution, capabilities, and architectural patterns of large language models (GPT-4, Claude, etc.) across multiple markdown files organized by model generation and capability domain. Uses a taxonomy-based organization (TEXT.md, TEXT_CHAT.md, TEXT_SEARCH.md) to map model capabilities to specific use cases, enabling engineers to quickly identify which models support specific features like instruction-tuning, chain-of-thought reasoning, or semantic search.

Curates a collection of effective prompts and techniques for image generation models (Stable Diffusion, DALL-E, Midjourney) organized in IMAGE_PROMPTS.md with patterns for composition, style, and quality modifiers. Provides both raw prompt examples and meta-analysis of what prompt structures produce desired visual outputs, enabling engineers to understand the relationship between natural language input and image generation model behavior.

Maintains a curated guide to high-quality AI information sources, research communities, and learning resources, enabling engineers to stay updated on rapid AI developments. Tracks both primary sources (research papers, model releases) and secondary sources (newsletters, blogs, conferences) that synthesize AI developments.

Documents the landscape of AI products and applications, mapping specific use cases to relevant technologies and models. Provides engineers with a structured view of how different AI capabilities are being applied in production systems, enabling informed decisions about technology selection for new projects.

Documents the emerging movement toward smaller, more efficient AI models that can run on edge devices or with reduced computational requirements, tracking model compression techniques, distillation approaches, and quantization methods. Enables engineers to understand tradeoffs between model size, inference speed, and accuracy.

Documents security, safety, and alignment considerations for AI systems in SECURITY.md, covering adversarial robustness, prompt injection attacks, model poisoning, and alignment challenges. Provides engineers with practical guidance on building safer AI systems and understanding potential failure modes.

Documents the architectural patterns and implementation approaches for building semantic search systems and Retrieval-Augmented Generation (RAG) pipelines, including embedding models, vector storage patterns, and integration with LLMs. Covers how to augment LLM context with external knowledge retrieval, enabling engineers to understand the full stack from embedding generation through retrieval ranking to LLM prompt injection.

Maintains documentation of code generation models (GitHub Copilot, Codex, specialized code LLMs) in CODE.md, tracking their capabilities across programming languages, code understanding depth, and integration patterns with IDEs. Documents both model-level capabilities (multi-language support, context window size) and practical integration patterns (VS Code extensions, API usage).

Documents computational requirements, hardware needs, and scaling laws for training and deploying AI models in INFRA.md, including FLOPS calculations, memory requirements, and cost-performance tradeoffs. Provides engineers with the technical foundation to estimate infrastructure needs for specific model sizes and deployment scenarios, covering both training infrastructure and inference optimization patterns.

Documents advancements in speech recognition (Whisper), text-to-speech, and music generation models in AUDIO.md, tracking model capabilities, supported languages, and integration patterns. Covers both transcription accuracy across languages and the architectural approaches used in state-of-the-art audio models.

Documents developments in agentic AI systems in AGENTS.md, covering agent architectures, tool-use patterns, planning approaches, and multi-step reasoning frameworks. Tracks how agents decompose tasks, interact with external tools, and maintain state across multiple reasoning steps, providing engineers with patterns for building autonomous AI systems.

Documents the techniques for adapting base language models to follow instructions through instruction fine-tuning (IFT) and Reinforcement Learning from Human Feedback (RLHF), explaining how these techniques transform raw language models into chat-capable systems. Covers the architectural components (reward models, preference data collection, policy optimization) and their interaction in creating instruction-following models.

Maintains documentation of AI benchmarks and evaluation metrics for assessing model performance across different domains (language understanding, code generation, image quality, etc.), enabling engineers to understand how models are compared and what metrics matter for specific use cases. Covers both standard benchmarks (MMLU, HumanEval) and domain-specific evaluation approaches.

Catalogs key AI datasets used for training and evaluating models across different domains (language, vision, code, audio), documenting dataset characteristics, licensing, and use cases. Enables engineers to understand what training data is available for different tasks and how dataset choices affect model capabilities.