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
Cloudflare Clef How A Decision Model Differs From An LLM
Cloudflare's Clef is billed as a "decision model", and it is easy to read that as just another LLM with a new label. It is not. An LLM answers a classification question by writing out its answer; Clef scores the answers you allow and hands back a pick and a confidence. This is what that difference actually is, what it buys you, how the two fit together in an agent, and when Clef is the wrong tool.
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.
Why You Should Know About MCP Apps And When To Use Them
AI assistants can now show a real, clickable interface from someone else's product right inside the conversation — a chart you can drag, a form you can fill in, a preview you can approve. That is MCP Apps, the open standard for putting a product's own UI inside Claude, ChatGPT and a growing list of other AI hosts. This is how it works, why it matters if you ship software, and the handful of situations where it is the right tool rather than a gimmick.