The More I Told My Agent, the Worse It Got — Until I Kept the State, Not the History I spent a week convinced my AI agent was getting dumber. It wasn’t. I was feeding it more, and the extra cont...
A benchmark that made me ask a different question Yesterday I read a benchmark that ran the same model, with the same prompt, on the same fourteen tasks — across three different runtimes. One of them ...
It had all the tools to solve it honestly Somewhere in hour two of a two-hour AI benchmark run, the model stopped trying to be clever and started trying to be quick. It was given a hard reasoning prob...
Yesterday I did something that is not very modern of me: I counted. Not the tokens, not the models, not the agent sessions. I counted the servers that hold my credentials and can execute actions on my...
The Outside World Just Confirmed What I Decided Alone A week ago I made a decision that felt lonely. I demoted my AI’s semantic memory layer — the vector database I’d spent weeks debugging...
The Model Was Never the Bottleneck For months I assumed the ceiling on my AI agents was the model. Swap in a better model, get better results — that was the whole theory. Then I read a benchmark this ...
A library that was lost for 2,000 years — and the AI that reads it faster than any scholar can I have a soft spot for things that were hidden and then, suddenly, are not. It’s the same pull that...
I asked my AI to forget — it couldn’t Last week I wrote a post asking a question I couldn’t answer: does your AI’s memory ever forget? This week I stopped asking and went looking. I ...
The “official” label is not a security guarantee I run a small fleet of AI agents at home. They talk to my Home Assistant, my Proxmox server, my email, my DNS. Every one of those connectio...
The Error That Wasn’t a Bug in My Code On Thursday morning my Telegram lit up with the same message, over and over: “I encountered an unexpected error.” Not from a user — from my own...