Every tests a probability-output foundation model: 25x faster, ~600x cheaper than Fable
danshipper · x · 2026-09-16
Dan Shipper says Every has been testing a new kind of foundation model from typesafeai that outputs probabilities instead of words — like a code linter for knowledge work. In their tests it ran 25x faster at nearly 600x lower cost than Fable for similar jobs, usable as a judge for code quality, AI-isms in writing, or content interest. The quoted thread explores whether a writing model could use such probabilities mid-generation to mimic an author's word-by-word decisions, potentially a big upgrade for AI-assisted writing.
More from Models
- Why OpenAI must copy Google's long game to keep up with Anthropic — haider1 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02
- Yacine calls Terra High 'kind of an insane model' — yacineMTB · 2026-11-02
- Running DeepSeek V4.1 on a single H200 at $5.30/hr — daluoseo · 2026-11-02
- Leaked Fable 5.5 checkpoint video called 'pure code' — 'will change the game' — kimmonismus · 2026-11-02
- Claude Opus 5.5 quality complaints spark debate on why continual learning is so hard — JeremyNguyenPhD · 2026-11-02