Thoughts
Short notes on state, memory and AI agents that work for longer than a demo.
ThoughtsWhy AI Models and Agents Get Worse the Longer They Run
AI models and long-horizon AI agents get worse the longer they run. The context fills with old versions of every fact, and each call burns reasoning to work out which one still holds.
5 min readThoughtsThe Three Intelligences
Long-running AI needs three things: reasoning, memory and state. We scaled the first two. AI agent state got skipped, and that is why agents fall apart.
2 min readThoughtsMemory Isn’t State
AI agent memory remembers everything, including what is no longer true. State keeps only what still applies. Agents need both, and most only have one.
2 min readComing soon
Dylan Telano: Founders You Should Know
The story behind Cricket.
Coming soon
Make AI Write in Your Voice
Your voice is state too.
Coming soon
The Cheapest Model That Gets It Right
Cost per successful task, not per token.