logoalt Hacker News

cbg0today at 8:06 PM1 replyview on HN

But is the score really reflective of the quality or are both models benchmaxxing?


Replies

bermuditoday at 8:44 PM

Muse 1.2 wrote a terrible "smart summaries" extension for my pi setup. It was sending every single steamed chunk for summarization instead of waiting for the full CMD.

This is an error I would expect from sonnet 4, not a model that was supposedly just a few points behind sol.