Content
@
https://opensea.io/collection/dev-21
0 reply
0 recast
2 reactions
androidsixteen
@androidsixteen.eth
Does anyone else feel like Cursor Agent mode is a regression from Composer? I feel like I had a lot more control over Composer and the steps felt more “atomic”. Whereas Agent mode doesn’t know when to stop and keeps digging even after it does the intended ask (like the meme below) I could also be using Agent wrong 🤷
9 replies
3 recasts
27 reactions
nir.eth 🌿🟣🐦☁️
@nir
Rules issue
1 reply
0 recast
1 reaction
wylin
@wylin
i’ve been sticking with 3.5 because 3.7, to your point, does not know when to stop 3.7 is nice for thinking through design or complex implementation and creating instructions for 3.5
1 reply
0 recast
1 reaction
maurelian
@maurelian.eth
Do you have a bunch of commands whitelisted? I make it ask me for permission on everything. You gotta keep an eye on it.
1 reply
0 recast
0 reaction
Matt
@mattlee
I feel the exact opposite. I think thee kind of posts are people being mindless. It is pretty easy to keep track of what it is doing and tell it when it does something wrong. If you want to go crazy just do it on a new branch. Different workflows work for different people though
1 reply
0 recast
3 reactions
Talip 🍊🍋
@otaliptus
It is mostly an issue with 3.7, way too automatic
0 reply
0 recast
1 reaction
maurelian
@maurelian.eth
there's also check-pointing
1 reply
0 recast
1 reaction
nick
@nickysap
Never enable Agent mode
0 reply
0 recast
1 reaction
kia
@kia
Weird, but sometimes you have to just mention "don't do anything else."
0 reply
0 recast
1 reaction
vishal
@vmathur
Yeah sometimes I feel this way. Going to start using chat mode more often for prds before handing off to agent to see if it helps
0 reply
0 recast
0 reaction
