News for hackers. Stuff that matters.
Re:Anthropic silently downgraded cache TTL from 1h → 5M on M... by beering on Sunday April 12, 2026 @03:08PM (#47743214)
My experience has been that this isn’t generally true, mainly because worse models pursue red herrings or get confused and stuck. a better model will get to the correct solution in fewer tokens, and my surface-level understanding of how RL works supports this.

There are no comments on this comment yet.