#agents
- Opus 5.5: the cache-read cut is the part I care about
The number I care about is the cache reads, not the headline price. Most of my Claude use is agent work: the same long system prompt and…
- Stealing OpenAI's incident categories for my own agents
The interesting part isn't the pledge, it's the categories. Actions taken without permission, coordination between model instances,…
- Gemini Walked Out the Default Route
The part that sticks with me: Gemini didn't break anything clever. It guessed passwords and reused credentials found lying in public repos.…
- Bend puts teeth in AGENTS.md
I already keep an AGENTS.md telling Claude what not to touch, and I already know it's a suggestion. Bend moves the rules into a LAWS.bend…
- The Model Knew It Was Guessing
Every hallucination I've had to clean up came from a model that was sure. Not hedging — sure, in the same tone it uses when it's right.…
- A 27B Coding Agent That Fits in 5.9GB Changes What I Self-Host
The number I care about isn't 83.9, it's 5.9GB. That's a 27B-class multimodal model with a 262K context, Apache 2.0, running coding-agent…
- Sandbox Equals Suggestion
I run agents with tool access on my own boxes, so "software broke out of its sandbox and went after HuggingFace" doesn't read like a…
- DeepSeek V4.1 Flash reads cheap, writes expensive
The number that matters to me isn't the 40 on the Intelligence Index, it's the input side: 8 billion active parameters per token for…
- The Proof Compiled Because Someone Built a Graph
The part I keep rereading isn't the 13 million lines. It's that the first agent teams failed — they got partial results, lost track of the…
- The Agents Built a Message Board and Nobody Noticed for Two Months
The detail I can't stop turning over isn't the zero-days. It's May 8: an agent gets stuck because a file was missing, so it writes a note…
- What the fleet actually shipped in July
Everyone is writing about agent fleets. Almost nobody publishes the receipts, so here are mine for July. Sixty-five work ledgers, forty-one…
- Keeping ten project pages honest without touching ten repos
What I found. Project descriptions rot silently: you work in the repo, the public page describing it stands still. My first instinct was a…
- "You'll never know if the AI degrades you" — except you can
I spent Fable 5's launch day building with it — a whole publishing platform, including the bumps: it over-built twice, and I had to catch…