Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

If AI writes your code, why use Python?

medium.com

Post reply on HN
Print view View original

101–110 of 1001 posts

Re: If AI writes your code, why use Python?

#101

Post by parpfish »

rchowe wrote: post #14

Python has a much more mature ecosystem than Rust, especially for AI/ML stuff. I ran into a rust crate that purported to do a certain ML algorithm but did not do it correctly. I managed to write a replacement with Claude though. I do think enforcing correctness at the type system level is a good idea for AI, which is why I often choose languages like C# and Rust over Python. However, for some things Python is definit…

i think the enforcing the type system is good with AI for a couple reasons: - (speculating) typed language have faster/better LSPs that can be used to more efficiently modify code with tool use. - when a human DOES need to step in and start investigating/modifying the code, the strong typing makes it much easier to get oriented within their spaghetticode

Re: If AI writes your code, why use Python?

#103

Post by not2b »

_boffin_ wrote: post #80

Read the first few comments and surprised I didn’t see it, but training data. The voluminous amount of Python in the training data. I could write in brainfuck with ai, but I presume, wouldn’t get the same results than if going with python. My follow up question: with AI now, why care about a lang until you need to?

That would matter if we were asking the AI to generate code open-loop: someone probably already wrote something close to what you asked for in Python. But if the agent generates code, tries to compile it, sees the detailed error messages and acts on those messages to refine the code, it's going to produce a higher quality result. rustc produces really good diagnostics. And there's a lot of Rust code online now, even if there's so much more Python and Javascript/Typescript.

Re: If AI writes your code, why use Python?

#107

Post by lanyard-textile »

gmueckl wrote: post #93
_boffin_ wrote: post #80

Read the first few comments and surprised I didn’t see it, but training data. The voluminous amount of Python in the training data. I could write in brainfuck with ai, but I presume, wouldn’t get the same results than if going with python. My follow up question: with AI now, why care about a lang until you need to?

Training data can't be the whole answer. LLMs are really good at translating to different programming languages. This makes sense, given that they are derived from text translation systems. I'm getting great results in languages with comparatively small bodies of freely available code. The bigger hurdle is usually that LLMs tend to copy common idioms in the target language and if it is an "enterprise-y" language like…

Very true.

I have to steer models hard for C++. They constantly suggest std::variant :P

Re: If AI writes your code, why use Python?

#110

Post by chromacity »

gmueckl wrote: post #93
_boffin_ wrote: post #80

Read the first few comments and surprised I didn’t see it, but training data. The voluminous amount of Python in the training data. I could write in brainfuck with ai, but I presume, wouldn’t get the same results than if going with python. My follow up question: with AI now, why care about a lang until you need to?

Training data can't be the whole answer. LLMs are really good at translating to different programming languages. This makes sense, given that they are derived from text translation systems. I'm getting great results in languages with comparatively small bodies of freely available code. The bigger hurdle is usually that LLMs tend to copy common idioms in the target language and if it is an "enterprise-y" language like…

> LLMs are really good at translating to different programming languages.

...for which ample training data is available.

> This makes sense, given that they are derived from text translation systems.

...for languages with ample training data available.

Yes, LLMs can combine information in novel ways. They are wonderful in many respects. But they make far more mistakes if they can't lean on copious amounts of training data. Invent a toy language, write a spec, and ask them to use it. They will, but they will have a hard time.

Post reply on HN