Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> software dev as we know it is about to disappear soon

Pushing back on this a bit. We see promises and people working on this. But I haven’t seen anything definitive yet, and LLMs have their own existential threats around amount and quality of data. Recent article involving trying to get LLMs to reason about law required very fine task decomposition to get move forward. What we don’t know is whether doing this and then handing it to an LLM is as beneficial to humans in speed/quality/feedback as simply doing it yourself. Have already seen people saying that copilot’s interaction loop short circuits actually thinking about the problem.

Regardless, hobbies outside of work are absolutely essential in this absurd time. The author made some beautiful things.



Hobbies outside work can still be coding. Code is not the same as it was with LLMs but it’s more effective for work and outside work. The LLMs just help but for me they don’t make coding less enjoyable outside modern web crap that is.


Why do LLMs make working on modern web crap less enjoyable?


Too many hallucinations because changes in fast changing libraries. It makes up functions that were removed and libraries that have been deprecated. With robust stuff that doesn’t happen. It is frustrating. Even copilot regularly includes some react lib that doesn’t work anymore for the past 3 years because it depended on old stuff that is full of security issues, bugs or doesn’t work on a new node etc etc. So then I spend more time on finding what is the newest (greatest … cough) thing to replace it than I would have done just searching google.


It’s funny because a big draw of React is the sizable user base and library count, but that ends up being a double edged sword when using LLMs for codegen.


Well, if they are not up to date I guess with the latest; it changes so fast and there are so many examples of all different flavours of how to do something... I guess they will find a mechanism which will make newer info more relevant and older info more forgotten in some cases and also a way to draw in the latest all the time. My problem is more the not built/designed etc here issue; when you have a react WidgetBlah library and someone else also wrote one, there are reasons you rolled your own (often also not but ok), but why didn’t you keep the api the same. People talk about features here as a reason for breakage but when I compare a breaking feature change (for instance, a react component sig changed from one version to another) then I hardly ever see a reason why that was not made backward compatible. I have complained about this in many GitHub issues and the answer is usually ‘this way is better, just refactor it: it’s easy’. Sure it’s easy but it’s work and this happens a little too often. Sometimes I would like Java standard bodies and voting about api changes and this is one of those.


RAG and large context sizes mitigate this well enough for me. Ingest the library's docs (and maybe a sizable chunk of your codebase) and use that to get better LLM output that isn't out of date or hallucinated.


It doesn't matter, it was never about LLM's, it's that tech holds special political powers across nations. Big tech can break laws and destroy people's lives and nobody is ever punished or regulated.

Software is in a race to the bottom because users have little market choice. LLM's are just the excuse, but in reality late stage capitalist economics demands that this happen somehow. Wether it be in the form of cheap labor or automated labor. You need to have political and physical leverage over the corps to force them into being sustainable.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: