←back to thread

Generative AI coding tools and agents do not work for me

(blog.miguelgrinberg.com)
399 points nomdep | 2 comments | 17 Jun 25 00:33 UTC | HN request time: 0.546s | source
Show context
socalgal2 ◴[17 Jun 25 05:48 UTC] No.44296080[source]▶
> Another common argument I've heard is that Generative AI is helpful when you need to write code in a language or technology you are not familiar with. To me this also makes little sense.

I'm not sure I get this one. When I'm learning new tech I almost always have questions. I used to google them. If I couldn't find an answer I might try posting on stack overflow. Sometimes as I'm typing the question their search would finally kick in and find the answer (similar questions). Other times I'd post the question, if it didn't get closed, maybe I'd get an answer a few hours or days later.

Now I just ask ChatGPT or Gemini and more often than not it gives me the answer. That alone and nothing else (agent modes, AI editing or generating files) is enough to increase my output. I get answers 10x faster than I used to. I'm not sure what that has to do with the point about learning. Getting answers to those question is learning, regardless of where the answer comes from.

replies(13): >>44296120 #>>44296159 #>>44296324 #>>44296351 #>>44296416 #>>44296810 #>>44296818 #>>44297019 #>>44297098 #>>44298720 #>>44299945 #>>44300631 #>>44301438 #
plasticeagle ◴[17 Jun 25 07:06 UTC] No.44296416[source]▶
ChatGPT and Gemini literally only know the answer because they read StackOverflow. Stack Overflow only exists because they have visitors.

What do you think will happen when everyone is using the AI tools to answer their questions? We'll be back in the world of Encyclopedias, in which central authorities spent large amounts of money manually collecting information and publishing it. And then they spent a good amount of time finding ways to sell that information to us, which was only fair because they spent all that time collating it. The internet pretty much destroyed that business model, and in some sense the AI "revolution" is trying to bring it back.

Also, he's specifically talking about having a coding tool write the code for you, he's not talking about using an AI tool to answer a question, so that you can go ahead and write the code yourself. These are different things, and he is treating them differently.

replies(8): >>44296713 #>>44296870 #>>44297074 #>>44299662 #>>44300158 #>>44300604 #>>44300688 #>>44301747 #
1. kypro ◴[17 Jun 25 09:01 UTC] No.44297074[source]▶
The idea that LLMs can only spew out text they've been trained on is a fundamental miss-understanding of how modern backprop training algorithms work. A lot of work goes into refining training algorithms to preventing overfitting of the training data.

Generalisation is something that neural nets are pretty damn good at, and given the complexity of modern LLMs the idea that they cannot generalise the fairly basic logical rules and patterns found in code such that they're able provide answers to inputs unseen in the training data is quite an extreme position.

replies(1): >>44299084 #
2. fpoling ◴[17 Jun 25 13:40 UTC] No.44299084[source]▶
Yet the models do not (yet) reason. Try to ask them to solve a programming puzzle or exercise from an old paper book that was not scanned. They will produce total garbage.

Models work across programming languages because it turned out programming languages and API are much more similar than one could have expected.