Micheal Lanham·16h agoAn LLM Rewrote 0.016%Weight-Space Programming, Day 1 of 7: one headline sold two different abilities, and a five-cent picture named the game.
Micheal Lanham·1d agoThe Busy Wednesday Problem: How Confounders Teach Your AI Agent SuperstitionsInstinctual Learning, Part 9 of 9: why a tired night’s low mark must be subtracted before your agent learns a single thing about the food.
Micheal Lanham·2d agoImagine Before You Act: What Tolman’s Rats Teach AI Agents About World ModelsInstinctual Learning, Part 7 of 9: keep a model of the world before the task needs it, then check the plan against it before you act.
Micheal Lanham·2d agoStop Stuffing Transcripts Into Your AI Agent: Why Contextual Learned Memory Beats Conversation…Instinctual Learning, Part 8 of 9: three chapters, one conversation-history baseline, and what a few lines of learned state did instead.
Micheal Lanham·4d agoYour AI Agent Will Never Order the Korean Food: Thorndike’s Cats, Operant Control and ExplorationInstinctual Learning, Part 6 of 9: once an agent’s predictions steer its requests, it changes the evidence it learns from, so it has to be…
Micheal Lanham·5d agoPavlov’s Dog Would Make a Better Recommender Than Your LLM: Prediction Error for AI AgentsInstinctual Learning, Part 5 of 9: a taste table that learns from surprise, tested while it only listens.
InBongquisitive TechbySourav Mukherjee·6d agoTeaching AI Agents to Evolve Without Cheating: Inside Google Research’s RRSI FrameworkHow Regularized Recursive Self-Improvement optimizes prompts, tools, memory, and control flow around frozen LLMs, boosting…
Micheal Lanham·6d agoThe Sea Slug That Beat a 30,000-Token Context Window: Habituation for AI AgentsInstinctual Learning, Part 4 of 9: how a response that fades with repetition and returns after rest becomes a small, testable component…
Micheal Lanham·Nov 2Stop Making Your AI Agent Think So Hard: System 1, System 2 and the Two-Model HarnessInstinctual Learning, Part 3 of 9: most agent decisions are familiar, so make them fast and let the harness decide when deliberation is…
Micheal Lanham·Nov 1Learning Isn’t One Thing: The 10 Mechanisms Evolution Built That Your AI Agent Is MissingInstinctual Learning, Part 2 of 9: name the mechanism behind a failure, and you know what to build and how to prove it learned.
