Hacker News Reader

Comment by BearOso | Hacker News Reader

LLMs can only reproduce what has been done before. For many tasks like web programming it can do a lot of what you need because it was trained on that data many times over. When you need to use a concept or knowledge that's fairly rare or oblique it will fail. That's pretty much what Carmack is saying--problem solving will continue to be a needed skill.

View on HN

I tell the computer exactly what I want done and it produces another program I can use to do that task.

Am I describing an LLM or a programming language?

Templates have been a thing for a long time and beyond being better than Google at finding them LLMs fall into the exact same problems those did:

If they don't exactly fit your goals you end up wasting a ton of timing fixing the edge cases.

this is really far from my experience coding with llms

i've often been able to get them to write working code to harness libraries i just wrote (so they definitely aren't in their training set) or programming languages that i haven't even implemented yet. i've fed them obfuscated code in one programming language and asked them to translate it into another—getting sometimes very buggy output, sometimes not. i've asked them for problem-solving approaches for novel problems and gotten reasonable answers—sometimes

Unless you’re at the cutting edge of your field, the rest of us are doing work that has been proven and solved by someone else.

Even when I’m working cutting edge, 99% of my work is still mundane. You still need to get all of the basic stuff in place.

Reply on news.ycombinator.com