Did something happened to auto mode?

Discussions
1

hi last months i used cursor and remember the cursor auto mode was not so good but now something happened that its terrible bad?

  1. its like total idiot where realising for it something need multiple askings most of the time.
  2. wants to make tons of edits always compared to other models and so need always tell that it should do only neccesarry things.
  3. image analysing is not good.

well i disappointed because i can run local model like gpt oss 20b that feels way more intelligent. so thats where i wanted to ask again about what happend to the idea of GLM 4.5 and qwen coder to use as auto modes? since they super cheap and good.
because this is really time wasting almost : (

2

Hey, we haven’t changed anything on our side. Can you confirm if this also happens in a new chat? You might be using some AI rules that could affect the model’s performance.

Also, could you share the request ID? For this, you need to disable privacy mode if it’s enabled, then reproduce the issue when it happens again and copy the ID.