Late Stage Capitalism

5919 readers

8 users here now

founded 5 years ago

MODERATORS

muad_dibber@lemmygrad.ml

Magpieinthesky@lemmygrad.ml

what to hate about AI (lemmygrad.ml)

submitted 1 day ago by big_spoon@lemmygrad.ml to c/latestagecapitalism@lemmygrad.ml

10 comments fedilink hide all child comments

generative AI vs just AI...is this the difference?

you are viewing a single comment's thread
view the rest of the comments

[–] ksynwa@lemmygrad.ml 4 points 1 day ago (1 children)

For coding I like to "talk to" Deepseek or Gemini for advice on approaches because most of the time when I need their help its for a problem that I have never worked before. I don't like prompting them for whole solutions because it robs of a learning opportunity and the code is often over weirdly overengineered. Like recently I asked it for thoughts on a python script I was working on and they added so much noise over useless shit like parametrising hardcoded values.

[–] CriticalResist8@lemmygrad.ml 3 points 1 day ago* (last edited 1 day ago)

the code is often over weirdly overengineered

With the GPT + deepseek combo it fixes that problem (in my layman's eyes); deepseek has a problem of overengineering especially if you don't scope it correctly but if it works on an initial script, it will mostly stay within it. It's also able to simplify GPT code.

For the life of me I have never been able to learn javascript, so when I need to code something for ProleWiki I just throw the problem at them. You can look into https://en.prolewiki.org/wiki/MediaWiki:Common.js our script file for what they came up with - the color scheme picker, the typeface picker, and the testimonials code. Color picker is a bit overengineered because we have a theme that should only be available for one month out of the year and it was simpler to hardcode it in.

I still have to think about the problem, if I don't scope it well enough they will come up with whatever they feel like. For the color schemes when I had the first custom theme working I told them to refactor the code so that we could add new themes in an array, and they came up with everything. So now I can add unlimited themes by just adding a line in the array.

Potential simplifications that they don't think about (and hence why it's good to know how the generated code works) is that there's no need for className and LabelId in the array, it could generate that from the value. But eh, it works.

edit - using it as a "copilot" is also a good use, though I find that sometimes it just utterly fails. It's still an RNG machine at heart. But if you get it to work, it can really help unlock your other skills and not get stuck on one part of the process.