News for hackers. Stuff that matters.

A comment on Provable Inference. Parent comment

Re:Provable Inference by pxmpxm on Wednesday November 04, 2026 @01:38PM (#50369716)
Customers care about model output being correct, Anthropic cares about model output being generated by Anthropic model.

This solves for the latter with a bunch of handwaving for the former.

[ Parent | on HN ]
Re:Provable Inference by elzbardico on Wednesday November 04, 2026 @01:46PM (#50369834)
You developer your agent implementation and more importantly, evaluated it, against a specific model.

You don't want all you eval work to go to waste just because the discount inference provider you're using decided AcmeModel4.23 is as good as the Anthropics GilgameshEpic7.2 that you used to validate your solution.

We already have trouble enough with model retirement.

[ Parent | on HN ]