[drob518]

Yep, surely humans write bad code, too. But not nearly as fast. This feels a lot like hiring oodles of hyper-productive junior developers. Are we going to get true productivity out of that or a scrambled mess? I don’t know the answer to that. Or maybe the models get so much better that it’s like hiring oodles of senior developers and architects and the payoff is real.

[pxc]

Humans just don't commit the same kinds of booboos as LLMs do. My team at work recently started using LLM agents for coding and I have since seen WTFs that I know no human would ever write.

It's not all bad! It's also enormously fun. I've been able to work on things I'd been putting off forever. When I can use LLM agents, I less often feel paralyzed by perfectionism, which is probably the biggest productivity boost I get. My own code has not decreased in quality, and I think that for the truly important things, neither has that of my colleagues.

But LLMs don't make junior dev mistakes. They make "my brain has worms in it" mistakes.

[skybrian]

It used to be that most college graduates had little or no experience working on large-scale projects. Now they’ll get to speed-run the issues involved in maintaining a large project.

[drob518]

So, is that a good thing? There’s still something to be said for experience, no?

[skybrian]

Yes, getting out of college already having some experience using coding agents seems good.