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

831–840 of 1001 posts

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

#831

Post by arikrahman »

slashdev wrote: post #786

The static vs dynamic language debate is decisively over and static has won. I called this out back in 2023, and I've only become more convinced since then. Statically typed languages are easier for the reader because you can see the types and quickly jump to their definitions (or even just hover over them in some IDEs). They're easier for the AI because they provide natural guardrails and feedback to guide it, as we…

Hard disagree, LLM's benefit from jacking in to the powerful nREPL dynamic languages in the Lisp family like Clojure, letting the agent manipulate the code in unprecedented ways.

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

#832

Post by svachalek »

prepend wrote: post #792
slashdev wrote: post #786

The static vs dynamic language debate is decisively over and static has won. I called this out back in 2023, and I've only become more convinced since then. Statically typed languages are easier for the reader because you can see the types and quickly jump to their definitions (or even just hover over them in some IDEs). They're easier for the AI because they provide natural guardrails and feedback to guide it, as we…

If static has won, why are dynamic languages more popular now (even since 2023). Comically, I’ve witnessed people say this since the 90s. For me, I don’t care about static because dynamic is easier. For the very few conditions where it matters, I’ll use static. Otherwise I like the simplicity of dynamic languages, especially python. IDEs provide support and jump to definitions in dynamic languages, too.

Programmers, at least the mass market programmers, have optimized for ease of writing code for many decades. It's a natural urge, but in the long run for successful applications, it's more important that code is readable and maintainable. As the years go by the initial cost of tapping out the code becomes more and more negligible.

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

#833

Post by vmg12 »

adam_arthur wrote: post #799
slashdev wrote: post #786

The static vs dynamic language debate is decisively over and static has won. I called this out back in 2023, and I've only become more convinced since then. Statically typed languages are easier for the reader because you can see the types and quickly jump to their definitions (or even just hover over them in some IDEs). They're easier for the AI because they provide natural guardrails and feedback to guide it, as we…

Strong typing has clearly won. However, verbose typing is likely a negative for LLMs. Algorithms written in "pseudo-code", aka a higher level language without type information, are far more readable to a human, and thus likely an LLM too. In regards to control flow and general concept of what code is doing, types provide very little info over well named variables. In fact they often impair understanding by breaking u…

> types provide very little info over well named variables

Types guarantee invariants at compile time, adding type info to a variable name is just a prayer that the next human or robot will enforce the invariants with respect to that type when it matters. This is like saying you don't need a saw stop because you should just avoid sticking your hand in the saw blade.

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

#834

Post by jmward01 »

Language wars are, in a word, silly. You use the language that your team knows best 99% of the time. All the arguments about performance and safety have fallen flat for me because the majority of times performance and safety are most impacted by complexity which is driven by how good people are with a language more than the language itself. I have seen rust and go that the team was uncomfortable with that led to slow and unsafe results where the same team could have shipped faster and safer python. Additionally, per line speed is driving actual performance less. Is that web page load slow because of python or the 16 API calls to LLMs and other big services you are making? Did switching to rust speed those calls up 10 or 100x? So the opening arguments are predicated on an assumption I don't accept. rust isn't 10-100x faster, it -can be- when rendering a fractal for fun but in practice is it?

To answer the title question though, why use Python? I think Python and higher level languages will become even more valuable since pairing up with code assistants requires keeping a higher level view of what is going on. You want to avoid the weeds, not emphasize them. You want the language used to be as easy for the human as possible so the human can stay involved. That means that my opening argument stays intact, use the language that the team knows best 99% of the time and only when needed force a language that is 'faster' when that is actually required.

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

#835

Post by gertlabs »

stingraycharles wrote: post #552
gertlabs wrote: post #413

Earlier quoted context omitted.

- The majority of the environments can be played where the agent writes code to work the environment towards a goal. So the model is problem solving, and it has to do so in a particular language, and some languages outperform others. We have a lot of data to back up the improved compiled language performance, but note these are for successful code submissions (failures are counted in a different metric). With the Lan…

I think my problem is that I’m not sure I understand whether you evals are testing language abilities or reasoning abilities. It seems to present results as if they’re testing language abilities, but the problems seem to be reasoning problems.

I'm not so sure there's a difference. The main thing we want to measure for LLMs is broad reasoning capability, but seeing how that ability changes under different constraints (like programming language) is the interesting part.

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

#836

Post by regularfry »

isityettime wrote: post #746
regularfry wrote: post #541

Earlier quoted context omitted.

I've noticed that with clojure(script) unless you specifically instruct them to keep nesting levels low, they can hit a point where they make a paren placement error and can't debug their way out of it. Although in my case while one model made the error then couldn't find what it had done, a second model that I switched to was then able to identify it and back it out. So I suspect this is a transient weakness in toda…

It's a bit of a pitiful way to fail. I wonder if diffusion models could handle parenthesis matching better. And I wonder if you could rig up tools for structural editing like with paredit.

It's one of the drawbacks of having quite so little syntax. There's just less to grab hold of.

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

#837

Post by BugsJustFindMe »

Because I understand and can review Python, so in Python I can more easily see when the generated behavior subtly deviates from the specification. I don't understand and therefore cannot do that with Rust, and the entire point of using AI in the first place is so that I can have an easier time without needing to learn new languages.

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

#840

Post by adam_arthur »

Geniuzz wrote: post #811
adam_arthur wrote: post #799

Earlier quoted context omitted.

Strong typing has clearly won. However, verbose typing is likely a negative for LLMs. Algorithms written in "pseudo-code", aka a higher level language without type information, are far more readable to a human, and thus likely an LLM too. In regards to control flow and general concept of what code is doing, types provide very little info over well named variables. In fact they often impair understanding by breaking u…

> Algorithms written in "pseudo-code", aka a higher level language without type information, are far more readable to a human, and thus likely an LLM too. What’s the basis of this claim? There are many many more lines of code LLM’s are trained versus pseudo-code. Also I agree, anecdotally the self-correction is key benefit from static types. If there is a mistake, it is caught at compile time and not at runtime.

It seems clear to me from first principles.

Humans are trained on human language. LLMs are trained on human language.

Thus something that is easier for a human to understand is likely easier for an LLM to understand.

That higher level language with well named variables reads more comprehensibly than code:VERB with:PREPOSITION types:NOUN, intermixed:ADJECTIVE, stems:VERB from:PREPOSITION first:ADJECTIVE principles:NOUN too:ADVERB

Post reply on HN