logoalt Hacker News

strangescriptyesterday at 3:50 PM1 replyview on HN

I find gpt-oss 20b very benchmaxxed and as soon as a solution isn't clear it will hallucinate.


Replies

blurbleblurbleyesterday at 4:38 PM

Every time I've tried to actually use gpt-oss 20b it's just gotten stuck in weird feedback loops reminiscent of the time when HAL got shut down back in the year 2001. And these are very simple tests e.g. I try and get it to check today's date from the time tool to get more recent search results from the arxiv tool.