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

271–280 of 1001 posts

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

#271

Post by maxdo »

Despite lots of influencers (Karpathy) I personally trust, the industry is taking the opposite turn for a reason:

https://platform.claude.com/docs/en/agents-and-tools/tool-us... Also Claude Cowork, etc.

1. You don't need compilation... run and test faster. Compilers were primarily built to prevent human error, and only very secondarily to guard your business logic.

2. Your validators quite often need to evolve. With Python or JS, this is a pydantic edit + run. Imagine 3–4 iterations of the same in Rust?

3. Composition. The entire cycle of software changes. An agentic system takes orders from a human, reads some kind of cache and snippets, writes/combines snippets, tests it, runs it, and fixes it. This almost pushes you toward snippets the size of a function, which still need to be covered with tests. I can easily build 10 function-sized Python files and write an agent that will mix and match 3 of them into a final result. With a compiled language, you'd need to compile 10 times — or store the binaries and think about what platform they'll execute on, etc.

I love the fact that the author is questioning this. No doubt the market for your favorite language will change. 80% of languages will go away — there is no market anymore for such a big variety of languages.

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

#272

Post by gwern »

GavinAnderegg wrote: post #211

It's strange to me that this blog post was written in English. If AI is available, why aren't we all communicating in Lojban? [0] It's an obviously superior language. What does it matter that many people already communicate in English and much of computing depends on that language? AI doesn't care about that. Plus, if you ever need to edit Lojban without AI, you should be able to pick it up in a few weeks, right? [0]…

This post wasn't written in English, it was written in AIglish. (For god's sake, please tell me you see it at this point and you don't need to punch the opening into Pangram to see '100% AI' to recognize it by now?)

So in a way it's proving its own point. Why painfully write out by hand in English when the LLM will do a better job by porting your English prompt to AIglish and get +235 points and #3 on HN?

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

#273

Post by agdexai »

tptacek wrote: post #19
an0malous wrote: post #17

The ideal language for AI coding: 1. Type safety as basic guard rails that LLM output is syntactically and schematically correct 2. Concise since you have to review a lot more code 3. Easy to debug / good observability since you can't rely on your understanding of the code. Something functional where you can observe the state at any moment would be ideal. 4. A very large set of public code examples across various dom…

Type safety feels like the big one; anything you can shift to static/compile-time regimes benefits agents immensely.

[flagged]

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

#274

Post by dnautics »

w0m wrote: post #267
gertlabs wrote: post #174

Earlier quoted context omitted.

Surprisingly, LLMs are actually much worse at reasoning in Python than other common programming languages for agentic coding tasks. Data here: https://gertlabs.com/rankings?mode=agentic_coding

Huh. This surprises me. Digging, it seems it looks like it comes down to interpreted + dynamically typed vs compiled and statically typed. TIL. If i were to start a truly vibe project; Go would have a significant leg up.

and yet dynamically typed elixir wipes the floor with go.

https://github.com/Tencent-Hunyuan/AutoCodeBenchmark/blob/ma...

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

#275

Post by stefanfisk »

BariumBlue wrote: post #210
gertlabs wrote: post #174

Earlier quoted context omitted.

Surprisingly, LLMs are actually much worse at reasoning in Python than other common programming languages for agentic coding tasks. Data here: https://gertlabs.com/rankings?mode=agentic_coding

Hah, I was just thinking that Python likely has a vast ocean of training data, but it's likely of lower quality, being much of it is written by beginners and those who aren't primarily programmers.

Reminds me of the time I asked Claude to write some Wordpress code for me. The results were…rough.

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

#276

Post by dnautics »

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…

> Training data can't be the whole answer.

Absolutely correct. Anthropic showed that 250 examples can "poison" an LLM -- independent of LLM activation count.

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

#277

Post by alexjplant »

CharlieDigital wrote: post #263
sshine wrote: post #58

Earlier quoted context omitted.

I almost always pick Rust. Recently I wrote a plugin for something that was written in Go. I could have used Rust, but Go for one felt right because if the thing turned out well, others would surely find more value in having one toolchain. The main reason is that you’re capable of reading it if you need to. And the recipient ecosystem expects a language. That’s why some data science communities pick R, MatLab, Julia,…

C# feels kinda nice because it's a good balance. Very good static typing, Roslyn analyzers, good tooling and decent hot reload (for a compiled language), really good ORM (EF Core) that implements UoW and reduces a lot of the need for transaction management (simplifying the code), flexible enough and fast enough for various kinds of use cases. Source generators are underrated as well since they can make the code very…

I've written this before, but C# is a great language held back by its culture. I'd say that 80% of C# shops I've seen used it because they were started in the late 00s by some IT guy with a surplus HP server and a dream whose whole world was Microsoft products. They were staffed by people with little knowledge of OSS products who self-identify as ".NET developers" instead of software engineers. Almost invariably they seem to have some gnarly legacy monolith that everybody is slowly chipping away at while old-timers continue deploying .NET services to IIS running on Azure VMs because it's a small evolution of what they've been doing for the better part of 20 years.

In the interest of fairness the San Francisco version of this is also a thing: a giant, untyped ball of Rails spaghetti from the same period running on Heroku that everybody has Stockholm Syndrome'd their way into loving because of Ruby's elegance and beauty. The burden is merely shifted from a large Microsoft to a series of small SaaS companies :-)

Exceptions to this rule exist (hence my "80%") and modern .NET is lovely but it seems that the non-Java/Python mindshare is now taken up by the Golangs and Rusts of the world. It's a true shame since I do love C# for basically being a better Java.

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

#278

Post by dnautics »

jryio wrote: post #125
gmueckl wrote: post #93

Earlier quoted context omitted.

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…

In higher dimensional vector space, yes it can. Dimensionality gets bizarre in 1000-D space. Similarity and orthogonality express themselves in strange ways and each dimension codes different semantic meaning. Therefore, if the training data is highly consistent you are by definition reducing some complexity and/or encoding better similarity. In Go the statement result, err := Storage.write(...) Is almost always goin…

It's a little bit old, but challenge you opinions about what matters for LLM agentic coding:

https://github.com/Tencent-Hunyuan/AutoCodeBenchmark/blob/ma...

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

#279

Post by goatlover »

maxdo wrote: post #271

Despite lots of influencers (Karpathy) I personally trust, the industry is taking the opposite turn for a reason: https://platform.claude.com/docs/en/agents-and-tools/tool-us... Also Claude Cowork, etc. 1. You don't need compilation... run and test faster. Compilers were primarily built to prevent human error, and only very secondarily to guard your business logic. 2. Your validators quite often need to evolve. With…

> 80% of languages will go away — there is no market anymore for such a big variety of languages.

That's kind of sad, but so many older languages have been declared dead only to hang in various niches or out of sight for decades.

Post reply on HN