My feeling (totally unproven) is that in the drive to make Sonnet 3.7 more "agentic", they've lost some of its ability to actually just stick to what you asked it to do. It seems that it "wants" (I know, it's not sentient!) to be more in the driver's seat now.

Definitely can be very annoying if you do just want it to execute on a set of instructions.

I don't know but if it wants to be in the driver seat, maybe it can pay the subscription fee for itself, because it is barely usable for anything I paid for before.

To me it's not a good deal that I pay for something that makes up the things it wants, and completely disregards what I asked. It's like the recipe for the worst SaaS you ever used.

This can be mostly mitigated with the right system prompt although I noticed occasionally the prompt will be ignored (~1/20).

Yes, the Agent mode is terrible. Have you tried using the Ask mode instead?

It seems to perform worse in Cursor, so maybe that's where the problem is.

Yeah, I am just considering cancelling my subscription and go back to ChatGPT.

wdym unavailable? it's still on api under `claude-3-5-sonnet-20241022`.

What do the numbers '3-5' in that name refer to if it's version 3.6?

There was never a Sonnet 3.6. They released what is commonly known as 3.6 as "Sonnet 3.5 (New)". Then, because so many folks ended up referring to it as 3.6, they decided to call this new model 3.7, as the mental territory for 3.6 was already occupied by 3.5 (New). Not confusing in the slightest!

Under unavailable I meant unavailable. I was talking about 3.6 not 3.5.

There is no 3.6. There is 3.5 and 3.5 (New), both of which remain available.

Ah, you are right, I found it (it was under the more menu on the UI).