News for hackers. Stuff that matters.

A comment on Claude Opus 4.7. Parent comment

Re:Claude Opus 4.7 by MattSayar on Thursday April 16, 2026 @12:58PM (#47796263)
I recognize the sarcasm. The data I can find says it's performing at baseline however?

https://marginlab.ai/trackers/claude-code/

[ Parent | on HN ]
Re:Claude Opus 4.7 by ACCount37 on Thursday April 16, 2026 @01:07PM (#47796398)
Yeah, that's my point. Humans are not reliable LLM evaluators. "Secret model nerfs" happen in "vibes" far more often than they do in any reality.
[ Parent | on HN ]