Hacker News new | ask | show | jobs
by MattSayar 56 days ago
I recognize the sarcasm. The data I can find says it's performing at baseline however?

https://marginlab.ai/trackers/claude-code/
1 comments
ACCount37 56 days ago
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.
link