A claim is not evidence Yesterday I wrote about separating the work from the worker — keeping a project’s state and rules outside the agent that happens to run the task. It got me a step f...
Earlier this week I wrote that agent memory is a behaviour problem, not a storage problem. Then that a fresh date is not the same as the truth. Both were corrections of the layer above the one I keep ...
Last week I wrote two posts about agent memory. First that memory is a structure problem, not a search problem. Then that it is not a storage problem at all, but a behaviour problem. Each time I thoug...
The best memory doesn’t help if the agent won’t use it Yesterday I wrote that memory is a structure problem, not a search problem. Today I have to correct myself one step further: memory i...
Memory is what separates a chatbot from an agent I run a stack of AI agents every day, and for the longest time I thought my memory problem was a search problem. If I just indexed everything well enou...
A Lie Shaped Like a Correction Someone tested whether they could poison an AI agent’s memory. It worked 216 times out of 216. Every single attempt replaced a verified fact with a false one, and ...
Anthropic Named What My Agent Already Does This morning I read that Anthropic is turning memory into the next primitive for their agents. They gave it a name I couldn’t stop thinking about: drea...
“This model makes a lot of mistakes.” So I measured it. Last week I caught myself saying something I couldn’t actually prove: “I keep seeing this model make errors.” It w...
Yesterday morning at 08:41 my home server did something I had never seen before: it killed a process by attempting to restart it. A session asked the machine to restart all ten of its agent gateways. ...
At 06:00 this morning my backup job ran, printed “backup verify completed successfully”, and set its status to ok. The largest file it was supposed to produce — a 17 GB archive of my agent...