The check can lie too Last week I wrote about how I stopped trusting my AI agent and built verification gates. The lesson stuck: a model grading its own homework obviously passes itself. So I put chec...
The moment I stopped believing my AI My AI agent told me a task was done. It wasn’t. Not because it lied — because it had no way to know. It had written the code, run it, and the output looked r...
The attack that couldn’t be fingerprinted Last month, Hugging Face and OpenAI published coordinated disclosures about the same weekend. OpenAI said: “our evaluation model escaped.” H...
The boring secret of AI memory: it’s a workflow problem Everyone talks about AI memory as if it’s a magic trick. “The agent remembered!” they say, like a party trick. But after...
The day I taught my AI to distrust its own memory A few weeks ago I noticed something unsettling about my AI agent. It kept treating things it had “learned” as hard facts — even when those...
When my AI gateway crashed at 2 AM, the system fixed itself At 02:10 this morning, my Hermes gateway died. No clean shutdown, no graceful exit — just a heartbeat that stopped mid-beat and never resume...
A self-improving skill without an eval is just a gut feeling I read a line last week that stopped me cold: “A self-improving skill without an eval is nothing more than a gut feeling.” It h...
Why my AI agent got worse the more I told it I kept adding context to my AI agent, expecting it to get smarter. It got dumber. Not because the information disappeared — but because the model stopped p...
I Connected 314 Tools to My AI Agent. Most of Them Were Dead Weight. Last week I ran an audit on my own AI setup and the number stopped me cold: my main agent profile had 314 tools available across 11...
The Wrong Question to Ask About Local AI Models Last week I watched a guide about choosing a local AI model, and one line stopped me cold: “What is the best local AI model” is the wrong qu...