The Model That Cannot Write A Sentence
On this page
- Why a model is named after Jevons
- Two shapes of output
- The asterisk on "zero hallucination"
- 200x of what, exactly
- The try-on demo, and why it is the flattering case
- How a 40ms repaint is possible at all
- Calibration is the claim I would actually test
- The comparison the launch post does not run
- How to tell whether it is for you
Related Articles
What Is An Agent Harness? The Pattern Behind Every AI Coder
A deep dive into agent harnesses — the loop that wraps an LLM and turns it into something that can read files, run tests, and ship code. We break down the six parts, the turn loop, the design tensions, and build one in 30 lines of TypeScript.
Google Gemma 4 And TurboQuant Explained For Web Developers
A deep dive into Google's Gemma 4 open model family and TurboQuant KV cache compression — what they are, how they work, and why they matter for developers building AI-powered applications.
Give Claude Code A Voice
An agent that works for ten minutes has exactly two moments worth interrupting you for — it finished, or it is stuck waiting on you. Two hook events, two one-second voice notes, and about six lines of settings.json. Includes both sounds, playable here, and the details that will bite you if you wire this up carelessly.
Give Claude Code A Visual Language
Turning a client-rendered app into a server-rendered one is not a pull request. It is six of them, in an order that matters, over three weeks — and by the second week nobody can answer "where are we?" without twenty minutes of scroll-back. Here is the shape that fixed it — one outline artifact, one step per pull request, and a link that points both ways.