Every tests a probability-output foundation model: 25x faster, 600x cheaper than Fable as a judge
danshipper · x · 2026-09-16
Every has been testing a new kind of foundation model that outputs probabilities instead of words, pitched as a code-linter for knowledge work. It can act as a judge for questions like whether code meets standards, whether writing contains AI-isms, or whether a tweet is interesting. In testing it read the author's entire written corpus and checked it for 21 AI writing tells in under a second, running about 25x faster and 600x cheaper than Fable for similar jobs. The author calls it one of the rare new foundation-model flavors that's genuinely impressive.
Related event: TypeSafe's Probability-Output Model Runs 25x Faster at 600x Lower Cost(4 posts)→
More from Models
- Predictions for a Huge AI Week: Opus 5.2, Codex Bot, and a Cheaper Sol — daniel_mac8 · 2026-09-16
- Cartesia's new voice model family draws praise; WER alone can't capture context-correct speech — buckymoore · 2026-09-16
- Replication of no-CoT evals shows GPT-Astra makes a qualitative jump across all datasets — dhadfieldmenell · 2026-09-16
- Anthropic's Astra tops spend while OpenAI's Luna dominates token usage by a lot — gdb · 2026-09-16
- DeepSeekMath-V2 makes verification the product, scaling verifier compute ahead of the generator — le_james94 · 2026-09-16
- ChatGPT Plus Work Projects Bug Persists for Days While OpenAI Marks It Resolved — OnwardUpwardForward · 2026-09-16