jb55's avatar
jb55 _@jb55.com 3 months ago
Which brings me to my main complaint about opencode: you can’t swap between these modes easily like you can with claude code. Human-in-the-loop vs not. Bizarre design choice
jb55's avatar jb55
vibe coding is too binary of a term and is causing confusion. The way I’m starting to look at it is agentic coding with different levels of human-in-the-loop. Sometimes you want to be in the loop (pair/symbiotic programming) sometimes you don’t (vibe coding) vibe coding isn’t necessarily bad, its just bad for certain problems: ones where you should be in the loop. And yes i still think humans should still be in the loop. For now.
View quoted note →

Replies (7)

jb55's avatar
jb55 _@jb55.com 3 months ago
its wayyy too planny. maybe thats useful if you're doing a massive vibe session for lots of features. i'm not really using ai this way atm though
SatsAndSports's avatar
SatsAndSports 3 months ago
I've used both, but I don't understand Both have the Plan-vs-Build distinction. Are you saying that the prompts in Claude Code nudge it in a different direction, which you prefer?
jb55's avatar
jb55 _@jb55.com 3 months ago
you can’t switch between “ask permission to do something” vs not in opencode. It’s a config setting instead of a toggle. I don’t use claude code in a way that lets it steer, since i steer it on ~30% of the edits while its coding. I guess i could switch permission to ask, but i still like switching between that mode depending on the task at hand