[sally_glance]

Can't speak for OP but I tried providing ast-grep in the execution context of an execute_bash tool, but even with pretty aggressive steering most models just don't seem to use it a lot. More expensive/SOTA models or higher reasoning increases the chances but lowers speed and raises cost. Maybe due to training bias for exploration tasks?

[blurbleblurble]

Yes, I've tried this passive approach too and didn't dig much further after that. I thought maybe they'd figured out something more intentional in the prompting to enable these kinds of approaches.

[sally_glance]

I have a hunch model proficiency for a given CLI tool very much correlates with how many StackOverflow answers and blog entries providing examples for it there are...

[blurbleblurble]

My sense is that we're at a tipping point where instruction following is getting good enough to disrupt these old habits