[waleedlatif1]

I really hope sonnet 4 is not obsessed with tool calls the way 3-7 is. 3-5 was sort of this magical experience where, for the first time, I felt the sense that models were going to master programming. It’s kind of been downhill from there.

[lherron]

Overly aggressive “let me do one more thing while I’m here” in 3.7 really turned me off as well. Would love a return to 3.5’s adherence.

[mkrd]

Yes, this is pretty annoying. You give it a file and want it to make a small focused change, but instead it almost touches every line of code, even the unrelated ones

[artdigital]

Oh jeez yes. I completely forgot that this was a thing. It’s tendency to do completely different things “while at it” was ridiculous

[nomel]

I think there was definitely a compromise with 3.7. When I turn off thinking, it seems to perform very poorly compared to 3.5.

[Jabrov]

Can be solved with more specific prompting

[deciduously]

This feels like more of a system prompt issue than a model issue?

[waleedlatif1]

imo, model regression might actually stem from more aggressive use of toolformer-style prompting, or even RLHF tuning optimizing for obedience over initiative. i bet if you ran comparable tasks across 3-5, 3-7, and 4-0 with consistent prompts and tool access disabled, the underlying model capabilities might be closer than it seems.

[ketzo]

Anecdotal of course, but I feel a very distinct difference between 3.5 and 3.7 when swapping between them in Cursor’s Agent mode (so the system prompt stays consistent).