Content
@
https://opensea.io/collection/dev-21
0 reply
0 recast
2 reactions
greg
@gregfromstl
Cursor is so bad lol
9 replies
0 recast
16 reactions
Haardik
@haardikkk
Why
1 reply
0 recast
1 reaction
greg
@gregfromstl
The more I push it the more I’m disappointed (as is the case with every LLM). Just stupid lazy mistakes. Horrible quality in even the best cases. No “agent workflow” comes even close to the accuracy of tab completion which isn’t unique to cursor And its slow as hell
1 reply
0 recast
3 reactions
Haardik
@haardikkk
I think it depends on how youre using it. It generally doesn't work well on big projects or when youre using terminology it may not know. I use it mostly for bootstrapping or early stage projects, or tell it to explain a code architecture for smth I wanna do without editing any of my files - works well for those use cases
1 reply
0 recast
0 reaction
greg
@gregfromstl
But big projects are the real ones. Anyone can take a project from 0 to 1, maintaining and improving legacy systems is the hard part
2 replies
0 recast
4 reactions
Haardik
@haardikkk
Oh for sure - im just telling you what its actually good for vs what its not right now I think the assumption is LLMs will just get better over time
0 reply
0 recast
1 reaction
androidsixteen
@androidsixteen.eth
Strong agree. Useful for creating a quick hacky thing But when you need to architect something, generally useless and almost always overly-eager, glazing the codebase with nonsense My main gripe is that the "Ask" mode is the most useful (since it's like SparkNotes for Stack Overflow), but they keep pushing "Agent"
2 replies
0 recast
2 reactions
