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…
