Using LLMs to vomit out all of your code into one commit is vibecoding. It’s clearly vibecoding when there weren’t even multiple commits. No trial and error, no refinement, just one giant dump.
Yeah, I completely agree there. Just like with regular coding, you have to go slowly, implement functionality in small focused chunks, review, and iterate.
And I’d also wait and see whether the project continues to be maintained before considering it. I just posted it because I thought it was neat, and might be worth watching to see how it develops, not that I’d use it over a more mature option at the moment.
I think we’re actually in complete agreement here.
I think so too. Maybe it will turn out fine, maybe not. Personally I’ve been looking at git histories and waiting a month or so before getting excited, just to see if it will pan out.
Yup, a month is a good first checkpoint for a project. People tend to get really excited early on, but then they either get bored and move on, or start running into some hard problems they didn’t anticipate. If somebody can work on a project for a month in sustained fashion, there’s good chance they’re actually using it themselves and will have the motivation to keep going.
Thank you so much for highlighting a hypothetical problem which only exists in your head. Seems like screeching about anything LLM related has now become the entire identity for some people. Really should find a new hobby.
Automation is very obviously not inherently anti-labor. The way automation is used under capitalism is, but I didn’t really expect any deep intellectual insights from you.
First of all, that’s obviously false. Second of all, go look at unemployment rates in USSR. You literally have no clue regarding the subject you’re attempting to debate here. However, even your whole premise is insane. We shouldn’t strive to do work for the sake of work. Automating toil away so people can spend their lives in a self directed fashion is unarguably a good thing. You’re just arguing for having what David Graeber called bullshit jobs here.
Yeah, I completely agree there. Just like with regular coding, you have to go slowly, implement functionality in small focused chunks, review, and iterate.
And I’d also wait and see whether the project continues to be maintained before considering it. I just posted it because I thought it was neat, and might be worth watching to see how it develops, not that I’d use it over a more mature option at the moment.
I think we’re actually in complete agreement here.
I think so too. Maybe it will turn out fine, maybe not. Personally I’ve been looking at git histories and waiting a month or so before getting excited, just to see if it will pan out.
Yup, a month is a good first checkpoint for a project. People tend to get really excited early on, but then they either get bored and move on, or start running into some hard problems they didn’t anticipate. If somebody can work on a project for a month in sustained fashion, there’s good chance they’re actually using it themselves and will have the motivation to keep going.
deleted by creator
Thank you so much for highlighting a hypothetical problem which only exists in your head. Seems like screeching about anything LLM related has now become the entire identity for some people. Really should find a new hobby.
deleted by creator
Ah yes, automation is anti-labor you are very intelligent.
deleted by creator
Automation is very obviously not inherently anti-labor. The way automation is used under capitalism is, but I didn’t really expect any deep intellectual insights from you.
deleted by creator
First of all, that’s obviously false. Second of all, go look at unemployment rates in USSR. You literally have no clue regarding the subject you’re attempting to debate here. However, even your whole premise is insane. We shouldn’t strive to do work for the sake of work. Automating toil away so people can spend their lives in a self directed fashion is unarguably a good thing. You’re just arguing for having what David Graeber called bullshit jobs here.