alt Hacker NewsIf AI writes your code, why use Python?
Comments
Rust is the way!
You can also use Julia. It is both easy for humans to write and read and for AI to generate because of the sane and powerful type system.
However, I expect that in the future some new language will take this role of dual use.
In my case: AI might write the code, but I have to architect the system, read the code, iterate and learn from it. Validate whether an approach makes sense, whether the chosen dependencies make sense, whether the testing is adequate and covers known failure paths ... good luck if this is a language and ecosystem you are not proficient in.
For the utilities I write it is faster to iterate without having to compile. When I get to the point where I'm done adding changing features, and performance is an annoyance I can always ask the AI to "rewrite this in Go". (I've never gotten to that point.)
Nice perspective on languages in the AI era. I think AI should be used to build best performing and highly scalable software systems.
Python is rather a UI for human logic comprehension. A mathematical notation of logics. Not a code to drive computer.
And prompt does not replace that.
So I can fix it when it breaks. I don’t understand anyone shipping real code without human review.
Give it 2 years, the ‘Blame the AI ‘ incidents will increase. Like an unfaithful partner you’ll always return to it
https://arxiv.org/pdf/2508.09101
tldr 2% average point lost on Rust compared to python, gap vary by model, go has a better upper bound but opus had it 3% below python.
benchmark is a bit old but research on why is there, article is just vibes
1) python is one of the foremost trained upon languages
2) it's practically verbose, not technically
3) it resembles pseudocode
4) batteries included shortcuts a lot of work
all of these reasons are a boon for LLM work.
Because I have to maintain it.
First one to vibe code a language for LLMs, by LLMs, wins a cookie?
Devs still have to maintain this code, the Python devs can definitely get the LLM to write (some kind of) Rust, but when it goes wrong and you hit the wall with the LLM then they can will have to learn Rust which might take a while, this sounds like a bit of a project risk.
Yes, and wondering why all the AI tooling is written in node.
Agreed. People should just use JavaScript since it's the one with the largest training set.
>Smaller languages like Zig, Haskell and Gleam don’t have the same quality when AI-generated (for now).
GPT 5.5 writes good haskell.
So we can read and debug it if we'd like?
If AI writes your code, why use frameworks?
One thing to consider:
The (well-known) Sapir–Whorf hypothesis (if dont know it, look it uop) is often invoked for natural languages, but there’s a pretty direct analogue for programming languages: the language you "think in" during solving a problem biases which abstractions and idioms you reach for first.
If you force an LLM to first solve a problem in a highly abstract language (Lisp, APL, Prolog) and only then later translate that solution to C++ or Rust, you’re effectively changing the intermediate representation the model works in. That IR has very different "affordance", e.g.
- Lisp pushes you toward recursive tree/list processing, higher‑order functions and macro‑like decomposition. (some nice web frameworks were initially written in LISP, scheme, etc...)
- APL pushes you toward whole‑array transforms, point‑free pipelines and exploiting data parallelism. (banks are still using it because of perforance)
- Prolog pushes you toward facts/rules, constraint satisfaction, and backtracking search. (it is a very high abstraction but might suit LLMs very well)
OK, and when you then translate that program into C++/Rust/python, a lot of this bias leaks through. You often end up with:
Rule engines, constraint solvers, or table‑driven dispatch code when the starting point was Prolog.
Iterator/functor pipelines and EDSL‑like combinators when the starting point was Lisp.
Data‑parallel kernels and "vectorized" loops when the starting point was APL.
In principle, an LLM could generate those idioms directly in C++/Rust. In practice, however, models are heavily shaped by their training distribution and default prompts. If you just say "write in Rust", they tend to regress towards the most common patterns in the corpus (framework‑heavy, imperative, not very aggressively functional or data‑parallel), even when the language would support richer abstractions.
By inserting a "thinking" step in a different paradigm, you bias the search over solution space before you ever get to Rust/C++. That doesn’t magically make the code better, but it does change which regions of the design space the model explores.
Same would also be true for python which is already a multi-idiomatic language. So it might be a good idea to learn a portfolio of different languages and then try to tackle a problem with a specific language instead of automatically using python/go/rust because of performance.
Something to consider...
p.s. how would a problem be solved when the LLM would have to write it first in erlang? Is it the automatically distributed?
p.p.s. the "design pattern" of the GoF comes automatically to my mind, which might be a good hint to the LLM to use.
Because once you leave Python or JS the quality of LLM-produced code degrades catastrophically.
This point only makes sense if you ship AI code without reviewing it. And if you're shipping AI code without reviewing it, you're going to run into much bigger problems than Python performance limitations.
1) I still have to comprehend it.
2) The corpus for the sort of applications I build is likely larger for Python than it is for C++ and Rust. Bigger corpus == more training data == better generated code.
3) The bottleneck in the applications I run aren't in the execution of the code; they're in the database/network latency.
4) I don't get anything extra for pushing Rust or C++ over Python.
Clojure is better. REPL + immutable defaults.
The most common languages in the training corpus will output the most reliably.
Honestly the bigger question is why we still write glue code at all. Let the agent orchestrate.
"Rust, [...], a build system that fought you"
I started using Rust in 2018 and I've never used a build system that fought me less, ever, before or after.
I stopped reading after that sentence.
if AI is generating text for you, why type?
Also easier to ship a binary like a cli
I stopped reading as soon as the claude C compiler was mentioned and it was claimed it can compile big projects. We all seem to exist on a different plane of reality
The article is likely to offend some people. But it's not entirely without premise. I've been shifting my attention to using languages that I'm not great at. What is the right language is a choice that is no longer dominated by what you know well. That can still factor that into your choice but there are other considerations now. One of which is that you will soon be generating orders of magnitude more code than is physically possible to manually review for you. You need to compensate for your own inability to review all code with proper guard rails and automated verification.
If you've managed software teams before, this won't be new. You just need to make sure the team does the right things. But you don't want to inject yourself on the critical path of everything. That's micro managing. People hate it and it's counter productive. You need to instead delegate responsibility and check that there is a good process with checks and balances that ensures things are done right.
If you are vibe coding, one shotting, etc. you are essentially operating without guards rails. You won't catch mistakes that are being made. You aren't doing the due diligence of verifying that what was delivered is the same as what was being asked for.
But if you do use guard rails, most of the engineering effort (i.e. your time) goes into building mechanisms to prove that what is being delivered is fit for purpose. And that needs to lean heavily on tools that verify things. Compilers, linters, test suites, headless browser based scenario tests, elaborate benchmarks, etc. Anything you can throw at this. The more the better. Even code quality issues are something you can catch and fix with tools. Code duplication issues are detectable. Poor cohesiveness and high coupling are simple metrics that you can optimize for.
With AI in the mix, all of that gets run automatically and you create a feedback loop where any introduced problem is more likely to be caught early. If you are a good senior engineer, you would have been doing all of this anyway. Because it compensates for your own inability to not make mistakes. With AI, you just need to do more of it.
I've dabbled with a few generated code bases in Go in the last few months. I have about 3 decades of experience with other languages. But not a lot of experience with Go. So, why did I pick it? It's not because I particularly like the language. It all looks a bit verbose and tedious to me and I've always preferred other languages. But since I'm not writing any code, I can step over that and make use of the fact that the compiler and build tools are really good and catch a lot of issues. By using Go, I'm leveraging the tool ecosystem around it. Which is really solid.
Because I don't read/write Go code, I'm forced to treat the system as a black box. Which means I just test the hell out of it in any way I can think of. When I don't know how, I ask the AI to suggest me ways. And it does, and I make it add those as well. My little system has performance benchmarks, end to end tests for everything, scenario tests testing complex scenarios, static code analysis, race detection, etc. And lots of unit tests. If I find any issue, I get paranoid about what else might be broken.
All I do is getting systematic about making it falsify the theory that it could all be broken by failing to produce a broken test scenario. I'm equally paranoid about code quality and technical debt. So, I make sure to check for that as well. Not manually of course. I simply ask the AI tool to do targeted reviews of code looking for duplication, adherence solid principles, etc. Any issues found are prioritized and addressed. With most quality issues, simply asking an LLM to look for such issues is surprisingly effective. Having guardrails just automates these checks and balances and makes them routine.
My inability to review at the line level no longer matters that much. Worse, me reviewing tens/hundreds of thousands of lines of code is probably counter productive. Even in languages I know well, it would take ages. I'd be the slowest part of the whole engineering process.
I dislike Go but I have to admit, it's a great language for AI generated code. Simple enough, it compiles quickly and it performs meh-well enough for most applications.
One of the reasons I dislike Go is because it's easy for most engineers to write really low grade code with it. But AI agents would probably not write the best code in any language anyway, so not much is lost.
Cute interesting take but I feel like it misses the point. Specifically, this makes sense where performance is necessary. Many projects have been written in suboptimal languages because the writers didn't want to learn lower level languages.
Still, not ALL projects benefit from such an approach and there are times when yes python is the right tool. Not just due to readability of humans but the other qualities that make it really good for small, iterative apps.
My take has never changed. Knowledge is cheaper than ever, but wisdom is as rare as ever. This is a great example of misunderstanding the former for the latter
A somewhat contrarian/pessimistic view: The hardest thing in any future of LLM generated code is going to be the verification step, and especially types of verification that require humans which are going to be the most expensive.
Therefore the "best" language is going to be whatever makes it easiest for humans to detect bugs, bad design, or that the "wrong thing" has been developed.
The LLMs just churns out non-idiomatic slop in any language.
It doesn't matter if the 800-line if statement is able to use pattern matching.
There's been a lot of progress on making coding agents able to solve problems when they can easily evaluate in a closed loop, we desperately need something similar for controlling complexity and using relevant abstractions.
Because LLMs fuck it up near-constantly and I need to review it
… because model tool calls is non-standard, so Python as the only tool call available works wonders
(Joke but also not a joke)
Interesting question.
AI doesn't really write code for me, but I do use them to brainstorm/ask questions. Though, I do not use Python. I have never been a fan of the language. I still think Python is a perfectly serviceable language, but it would solve no (important) problems I have ever had better than any other language.
I can see why Python is appealing to many people, and I applaud Guido for all the work and oversight over the years, but Python lacks a lot of the things I like in a language.
people don't write python because of the language. Some do but that's not the main reason. They do to utilise tools only exist in the ecosystem. AI changes nothing.
I had gpt-5.5 translate microgpt.py into a C++ version recently. I had to steer/convince it to use data oriented design to avoid excessive pointer chasing, but the end result was as expected: Now 500 LOC instead of 199, but speedup was 100x. That speedup is definitely worth doubling the line count. And frankly, modern C++ can read very nicely, even compared to Python.
Because I can understand and edit that code by hand if I need to.
I stay for the libraries
Slop begets slop?
As always, "it depends."
I'm using coding tools to build a complex media-intensive application. The approach I'm taking is to build a _reference implementation_ in Python, which is in its design specifics, constrained to use patterns which transliterate into the actual deployment targets (iPadOS/MacOS/Web).
Why start with Python?
Because I can read it, reason about it, and run it, trivially, which are Good Things for the reference. I intend to have multiple targets; I'd rather relate them to a source of ground truth I am fluent in.
For what I'm doing, there is also a very rich set of prior art and existing libraries for doing various esoteric things—my spidey sense is that I'm benefiting from that. More examples, more discourse.
I'm out of the prediction business and won't say this is either a good model for every new project, or, one I will need in another N months/years.
But for the moment it sure feels like a sweet spot.
Ask me again though, after the reference goes gold and I actually take up the transliteration though... :)
If you can use Python, why have AI write your code? :-)
you still need to look at the code oneday so id say c++ still would be a preferred target language even for ai. i know i hear a lot about rust but im still getting the idea its a niche language overall. i know people love it and point out its advantages, but sometimes good enough is good enough (i.e. c++)
Its unbeliebale that there are people possessing these types of thought processes, --- If AI can talk, why speak?
The article applies to a narrow case of a totally green field application that's going to be completely vibecoded. This is the only case where you reasonably can be indifferent to what the language is, and so you can abandon familiar Python and go with unfamiliar Rust. (If you _are_ familiar with Rust, the point of the article is moot.)
This "fair weather development" approach feels very risky if that application is going to be exposed to any serious usage. There WILL be a situation when things break and the AI will be powerless to fix it (quickly) without breaking something else in a vicious loop. There WILL be a situation where things work fine and tests pass with 3 concurrent users but grind to a complete halt with 1000 because there is something O(N^2) deep in the code. And you NEED a human to save your day (which requires also proper architecture for that to be possible in the first place). If you don't plan for this, and just hope for the best, then you are building nothing more than a toy. And if you plan for this, then it matters again what the language is, and whether your team is proficient in it.
Or maybe I too old fashioned or too behind the state of the AI art...