> My experience with Anthropic is that despite using Opus 4.6 and 4.7, most of t... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

gruez 77 days ago | parent | context | favorite | on: SWE-bench Verified no longer measures frontier cod...

> My experience with Anthropic is that despite using Opus 4.6 and 4.7, most of the time the performance is matching low B parameter Qwen.

Is this just the next level of the "they're serving quantized models!" theory?

varispeed 77 days ago [–]

Not a theory buy lived experience. You never know when you get the nerfed session.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact