Company
Every
Publication with its own AI evals desk
Taylor, head of evals at Every, ran Jev against Claude Fable 5.1 on his own writing on September 15, sending 37 documents with 21 questions apiece and getting 777 judgments back in under a second, for about a quarter of a cent.
Description sourced from
- AI Lately
“Taylor, head of evals at Every, ran Jev against Claude Fable 5.1 on his own writing on September 15, sending 37 documents with 21 questions apiece and getting 777 judgments back in under a second, for about a quarter of a cent.”
Named in 1 piece
Frontier Models
Graded by the Models It Replaces
TypeSafe AI left stealth with $40 million and a model that answers in typed decisions, skipping prose entirely, and its headline speed claim rests on agreement with two rival models.