Content
@
https://opensea.io/collection/dev-21
0 reply
0 recast
2 reactions
Ben Adamsky ðŸ’
@ba
I recently switched back to using cursor after swearing by claude code for months Using a combo of - cursor's new composer model - subagent git worktrees - voice dictation with wispr flow I'm now able to work way faster with multiple agents at once without any noticeable difference in code quality. It's crazy how much of a productivity unlock this has been. Also important to note that all agent code is sandboxed by default and has a strict allowlist on both native + mcp tools to prevent any unwanted db writes or pushes to git. I now just let it run wild knowing it can't break everything on me.
4 replies
2 recasts
58 reactions
alec.ethðŸ¤
@alec.eth
can't you run claude codes in cursor terminal...? been a minute but remember i had them both going at one point
1 reply
0 recast
3 reactions
Ben Adamsky ðŸ’
@ba
Yeah that's the setup I had before, but using cursor with their composer 1 model has been much faster/intuitive than claude code on sonnet 4.5 Also claude code's cursor extension is a bit janky, half the time the newline keybind is broken and the code diff is hard to work with since it's not native like cursor/warp
0 reply
0 recast
3 reactions