logoalt Hacker News

varispeedyesterday at 7:14 PM1 replyview on HN

It is my own anectodal. Few days something I worked on usually got one shotted or got quality result. Today it is very much going nowhere and is stuck in reasoning loops.

Probably someone should build nerf tracker, because this is quite common that models get substantially worse once PR hype wears off and they quantise them more or simply route requests to older models with system prompt changed to say it is Astra and not Sol etc.


Replies

EPWN3Dyesterday at 10:34 PM

So it's your own anecdotal experience, but someone should build a service to track it?