Elektrine lite

← Feed

@regehr@mastodon.social

Post #2001903

2026-05-04 03:27 UTC

@aburka @gwozniak well, being serious now, I'm trying to figure out what they're good at, if anything. and I really do find them useful for big, weird interfaces that I can never keep in my brain. other than cmake-- tikz, matplotlib, dockerfiles. there's just so much of this and I only deal with any given piece of it a few times a year. but I am capable of looking at what the LLM did and evaluating it.

Replies (3)

  • @aburka@hachyderm.io 2026-05-04 03:32

    @regehr @gwozniak what G and I were saying is it's a very slippery slope from "I just use it for the annoying stuff I can't remember" to everything and of course everything in the article you linked about cognitive debt and atrophy etc and all the externalities with the environment and the economy and the death of junior developer jobs I'm so tired of having this argument though

    Open ##2001904

  • @jpetazzo@hachyderm.io 2026-05-04 05:11

    @regehr @aburka @gwozniak In theory, yes, that sounds like a compelling argument (using LLMs for obscure stuff we don't have the time to learn). In practice, though? I teach docker and k8s, and whenever the time comes to write Dockerfiles, YAML manifests, and the like, I show students multiple techniques: editing examples found in the docs, generating them with tools, and now with LLMs. The LLMs invariably generate suboptimal results. At best they add some extraneous stuff that doesn't harm too much beyond readability and maintenance of the result; at worse the outcome is just broken in ways that are not immediately obvious. I can notice it and point it out to the students because I have a decade-ish of experience with these tools. Somebody with less experience won't know. (And no, it's not "getting better"; at least not in a game-changing way.) It's still useful as a stopgap (if some build pipeline needs a Dockerfile and you don't know how to write one, it might save you). Something I've been advocating for in that field is that you don't need the whole team to know the ins and outs of e.g. Dockerfiles, but you almost certainly need to have at least 1-2 people who are well versed with it. If you replace your in-house Dockerfile experts with Claude, the output will suffer, and you won't even be able to know how deep.

    Open ##2001915

  • @gwozniak@discuss.systems 2026-05-04 05:27

    @regehr @aburka I freed myself from the cat but it's too late to make my points now. I don't have the exact same feelings as aburka here. I have thoughts, of course. Later.

    Open ##2001916