Ask HN: How are you using LLMs or ML to improve your SWE?

Re:Ask HN: How are you using LLMs or ML to improve your SWE? by catlover76 on Sunday November 12, 2023 @05:00PM (#38244528)

Most of the time, I have not found the distillation from GPT-4 to be "sloppy".

> If you want to be an autodidact, seek out the information from primary sources, study it and organize it yourself. With GPT-4, you're essentially reading a sloppy cliffs notes of the topics. You'll be much better informed and be able to think more deeply about the subject matter if you adopt some ideas from Richard Feynman, wherein you try to explain what you think you know to a child, or at least someone with no knowledge of the subject. That will highlight the gaps in your understanding, and you can return to the source material to fill in the gaps.

The most immediate and fundamental problem with what you are suggesting is that it is infeasible. Nobody has time to learn everything they wish to at the level of depth they would ideally want. Nobody has time to read all the primary sources on which GPT-4 was trained. I find this so obvious I won't belabor the point.

I don't think any other tool can approximate the personalized "per-unit-of-time learning" afforded by a good LLM.

[ Parent | on HN ]

Re:Ask HN: How are you using LLMs or ML to improve your SWE? by ipaddr on Sunday November 12, 2023 @05:11PM (#38244615)

The topics you mentioned were picked up by others with gpt. Because they learned the pattern themselves they have a deeper knowledge then you. You might remember the prompted you used but someone else can identity the pattern and apply to other problems. You are cheating yourself out of learning.

[ Parent | on HN ]

Re:Ask HN: How are you using LLMs or ML to improve your SWE? by catlover76 on Sunday November 12, 2023 @05:26PM (#38244738)

The alternative to learning it using GPT-4 is not to learn it as deeply as other people did over much longer periods of time.

The alternative is whatever one can learn without GPT-4 in whatever amount of time is reasonable/allocated for it at the moment.

Like, take Docker. Yes, you would not be wrong to say that "by getting help from GPT-4 to do stuff, you won't learn it as well as people who didn't get that help and slogged through it over the course of 2 years at one of their last job", but this ignores that I probably will, over the course of the next several months, learn a lot about Docker in a fraction of the time it took the hypothetical other person.

I don't doubt that leaning too much on LLMs as a crutch may have negative effects, but I find this to be a surprising line of argument on a tech forum; there is such an obvious difference in efficiency between learning using an LLM versus the slog of other materials--again, aside from books, though I think they offer, ideally, a different kind of learning.

[ Parent | on HN ]

Re:Ask HN: How are you using LLMs or ML to improve your SWE? by ipaddr on Monday November 13, 2023 @11:13AM (#38251868)

I use gpt (3.5) and it's great but deep learning only happens when you add in friction and chatGPT makes things easy so you lose that step. For one off tasks use it but for others try to solve the puzzles yourself before you peak at the answer.

[ Parent | on HN ]