The Gate That Said No
Whether to adopt a tool you built is itself a decision under uncertainty, so it deserves a decision rule, not a leaderboard. I built a pre-committed, …
essaysbayesianaidecision-theory
Bayesian
Make Your OpenClaw Agent Cheaper, and Measure It Yourself
credence-pi is an OpenClaw plugin plus a local daemon that learns your agent and acts at two points by expected utility: it routes each turn to the cheapest …
essaysbayesianaidecision-theory
Make Your OpenClaw Cheaper and Harder to Fool
credence-pi is an OpenClaw plugin plus a local daemon that learns your agent's behaviour and governs its tool calls by expected utility: it blocks the calls …
essaysbayesianaidecision-theory
What a Regex Can't Do
The governor from 'The Brain is Opaque to the Body' now ships as an OpenClaw plugin: wasted tool calls blocked at precision and recall 1.0 on real sessions, …
essaysbayesianaidecision-theory
The Brain is Opaque to the Body
A first-pass body-brain architecture for governing a coding agent's tool_call hook with a Bayesian decision-theoretic brain. The wire schema is fixed by what …
essaysbayesianaidecision-theory
Three Types and a Funeral for Your Inference Library
What would it take to build an agent whose behaviour is derived from a few fundamentals the way physics is derived from conservation laws? Three types, four …
juliabayesianmachine-learningaiessays
Ninety-Six Percent Cheaper and Slightly Better
Credence-proxy sits between an agent and its LLM providers, learns which model is good for which category, and routes accordingly. On an OpenClaw benchmark it …
essaysbayesianmachine-learningai
The Prompting Gradient
Each prompting technique helps. Reasoning traces, strategy guidance, cross-question history --- each one improves accuracy and score. None of them closes the …
essaysbayesianmachine-learningai
The Agent That Invents Its Own Rules
Most agents are given a fixed set of decision rules. Credence's second tier generates candidate rules from sensor features, scores them by complexity, and lets …
juliaessaysbayesianmachine-learningai
Sixty-Two Percent Correct and Winning by a Hundred and Twenty Points
A Bayesian decision-theoretic agent scores lower on accuracy than every LLM variant it competes against --- and beats the best of them by 120 points. The …
essaysbayesianmachine-learningai
The Loop Problem
Every RL agent that has played a text adventure has tried to take the lantern fifty times in a row. The fix is not better exploration heuristics. The fix is …
juliabayesianmachine-learningaireinforcement-learning
Teaching Zork to a Bayesian
A Bayesian agent plays text adventures with four information sources and a VOI gate on every query. The LLM recommends actions. The mathematics decides whether …
pythonbayesianmachine-learningaiinteractive-fiction
The Bitter Lesson Has No Utility Function
I wrote about decision theory fading from AI. Hacker News said I was annoyed at Rich Sutton's Bitter Lesson. I wasn't. But the misreading proves the point.
essaysbayesianmachine-learningai
Why We Stopped Using the Mathematics That Works
Someone asked why decision theory stopped being widely used in AI. The answer involves ImageNet, academic departments, and the seductive power of not having to …
essaysbayesianmachine-learningai
How Decision Theory Cuts Your AI Agent's API Bill in Half
Most LLM agents use tools like a tourist uses a phrasebook. A few lines of probability theory can fix it.
pythonbayesianmachine-learningai
Agentic AI Is Neither Intelligent Nor an Agent
I built a Bayesian agent and set it against LangChain on a tool-use benchmark. LangChain got more answers right and still lost — by 120 points.
pythonbayesianmachine-learningaiessays
Evolution Discovers How to Think: A Philosophical Journey in Code
Part 2 of the Bayesian agent series. We confront the question of what should be designed versus what should be allowed to emerge, and discover that it's agents …
pythonbayesianevolutionsimulationphilosophy
Building a Bayesian Learning Agent That Teaches Itself to Eat
A visual demonstration of Bayesian inference and the exploration-exploitation tradeoff. An agent navigates a grid world, learning which foods are safe through …
pythonbayesianmachine-learningsimulationeducation