Sonnet 4 Opus fallback to Sonnet 3.5 (duplicate)

[stonianua]

It happened in the middle of the thread. It might be some fallback logic or what? The quality of solutions also reduced so I believe it uses 3.5 instead of Opus

[T1000]

There is no fallback thats inaccurate response from the model. Its not a bug but info from training data. The model knows only its name “Claude” and not which version or type.

This has been shown as false many times before:

Why is Cursor running system instructions that ask models to pretend to be other models?

Recently I noticed that my responses from Sonnet 4 sounded a lot like 3.5 instead. So I did some digging around and this isn’t the first instance of this kind of thing happening apparently? Cursor better have a good response to this - breaking trust is the best way to destroy your client base. [Screenshot 2568-05-29 at 22.41.16]

Claude 4 is reporting as Claude 3.5

Models are never aware of themselves as the data they are trained on doesn’t mention them - a bit of a catch-22! “Claude 4” is not a concept on the internet when they train the model, so it’s not aware of it’s own existence, and therefore falls back to saying it is Claude 3.5, as that is a model it is aware of from it’s training data. Rules may fix this, but it’s likely not worth adding a rule just to get it to state it’s real name - you are always talking to the model you pick in Cursor!