Comment by Workaccount2

8 months ago

I think a huge reason why LLMs are so far ahead in programming is because programming exists entirely in a known and totally severed digital environment outside our own. To become a master programmer all you need is a laptop and an internet connection. The nature of it existing entirely in a parallel digital universe just lends itself perfectly to training.

All of that is to say that I don't think the classic engineering fields have some kind of knowledge or intuition that is truly inaccessible to LLMs, I just think that it is in a form that is too difficult right now to train on. However if you could train a model on them, I strongly suspect they would get to the same level they are at today with software.

18 comments

Workaccount2

Reply
alganet  8 months ago

> I think a huge reason why LLMs are so far ahead in programming

Are they? Last time I checked (couple of seconds ago), they still made silly mistakes and hallucinated wildly.

Example: https://imgur.com/a/Cj2y8km (AI teaching me about the Coltrane operator, that obviously does not exist).

  • gcanko  8 months ago

    You're using the worst model when it comes to programming, not sure what point you're trying prove here. That's why when someone starts ranting how useless ai models are when it comes to coding I always assume they're just using inferior models.

    • alganet  8 months ago

      My question was very simple. Suitable for a simpler model.

      I can come up with prompts that make better models hallucinate (see post below).

      I don't understand your objection. This is a known fact, LLMs hallucinate shit regardless of the model size.

      2 replies →

  • aoeusnth1  8 months ago

    Are you intentionally sandbagging the LLMs to prove a point, or do you really think 4o-mini is good enough for programming?

    Even 2.5 flash easily gets this https://imgur.com/a/OfW30eL

    • alganet  8 months ago

      The point is that I can make them hallucinate quite easily. And they don't demonstrate knowing their own limitations.

      For example, 2.5 Flash fails to explain the difference between the short ternary operator (null coalescing) and the Elvis operator.

      https://imgur.com/a/xKjuoqV

      Even when I specify a language (therefore clearing the confusion, supposedly), it still fails to even recognize the Elvis operator by its toupe, and mixes it up the explanation (it doesn't even understand what I asked).

      https://imgur.com/a/itr87hM

      So, the point I'm trying to make is that they're not any better for programming than they're for chemistry.

      10 replies →