๐ AI
- AI basics โ introduction
- ๐ฌ Video ยท reading 5 min / video 4 min
- ๐ท๏ธ Terms: language model, dataset, parameters, AI/ML/NN, foundation models
- AI basics โ overview
- ๐ฌ Video ยท reading ~14 min / video 9 min
- ๐ LLM overview: use cases, internals (tokens, transformers), prompting, RAG, fine-tuning, chain-of-thought, model families, key terms, risks, trends
- ๐ท๏ธ LLM, transformer, token, temperature, prompt engineering, RAG, fine-tuning, RLHF, chain-of-thought, context window, hallucinations, multimodality, agents
- AI basics โ prompt engineering
- โฑ๏ธ ~7 min read ยท no video
- ๐ Zero-shot, few-shot, chain-of-thought, roles, step-back, where prompts come from; mind-map layout; accordions
- ๐ท๏ธ prompt engineering, zero-shot, few-shot, CoT, role prompting, step-back, in-context learning
- AI basics โ RAG systems
- โฑ๏ธ ~6 min read ยท no video
- ๐ Why RAG, pipeline stages, chunking, naive vs advanced RAG; accordions
- ๐ท๏ธ RAG, retrieval, embeddings, vector index, chunking, context-conditioned generation
- AI basics โ LLM agents
- โฑ๏ธ ~7 min read ยท no video
- ๐ Agent vs chat, planning / memory / tools, mindset, ReAct, multi-agent, who uses them; accordions
- ๐ท๏ธ AI agents, LLM, ReAct, tools, planning, memory, multi-agent systems
๐ฅ On Their Shoulders
Short digests from interviews, podcasts, and conferences on AI
- The Future of AI: Why Scaling Alone is No Longer Enough
- ๐ฌ Video ยท reading 12 min / video 8 min (original 52 min)
- ๐ฅ Participants: Nicholas Thompson, Eric Xing, Yoshua Bengio, Yuval Noah Harari, Yejin Choi
- ๐ท๏ธ Terms: scaling, reward hacking, world model, guardrail, AGI, anthropomorphism
๐ Mathematics
- BetterExplained - Part 1 - Intuitive Math
- BetterExplained - Part 2 - Arithmetic
- Essential math they’ll ask you at interviews from nareshka.ru
- Math with Bad Drawings โ overview of Ben Orlin’s books
- Math Analysis โ Example of Analysis (Finding ฯrยฒ)
- ๐ Slicing the circle into rings, unrolling into strips 2ฯr ร ฮr โ yields a triangle of area ฯRยฒ
- ๐ท๏ธ Integral, limits, area of circle
- Math Analysis โ Derivatives
- ๐ Without this you can’t understand how neural networks learn. Derivative, gradient, chain rule.
- ๐ท๏ธ Gradient descent, backpropagation