TypeSafe's probability-output model: 25x faster, 600x cheaper than Fable as a judge
danshipper · x · 2026-09-16
Dan Shipper of Every spotlighted TypeSafe's unusual foundation model that outputs probabilities instead of words — a 'code linter for knowledge work.' In testing it ran 25x faster at nearly 600x lower cost than Fable for similar jobs. Use cases include judging code quality, detecting AI-isms in writing, and scoring tweets. Shipper calls new foundation-model flavors this impressive rare, and points to Matthew Hammer's detailed vibe check.
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