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

ChatGPT Containers can now run bash, pip/npm install packages and download files

simonwillison.net

Post reply on HN
Print view View original

191–200 of 336 posts

Re: ChatGPT Containers can now run bash, pip/npm install packages and download files

#191

Post by simonw »

jacquesm wrote: post #189
fooker wrote: post #159

Earlier quoted context omitted.

I have worked on some of the most supposedly reliable codebases on earth (compilers) for several decades, and most of the code in compilers is pretty bad. And most of the code the compiler is expected to compile, seen from the perspective of fixing bugs and issues with compilers, is absolutely terrible. And the day that can be rewritten or improved reliably with AI can't come fast enough.

I honestly do not see how training AI on 'mountains of garbage' would have any other outcome than more garbage. I've seen lots of different codebases from the inside, some good some bad. As a rule smaller + small team = better and bigger + more participants = worse.

That's why the major AI labs are really careful about the code they include in the training runs.

The days of indiscriminately scraping every scrap of code on the internet and pumping it all in are long gone, from what I can tell.

Re: ChatGPT Containers can now run bash, pip/npm install packages and download files

#192

Post by llbbdd »

halfcat wrote: post #165
zx8080 wrote: post #145

Earlier quoted context omitted.

> probably 20+ percent of code written on my team is by an LLM. it's great for frontends Frontend has always been shitshow since JS dynamic web UIs invented. With it and CSS no one cares what runs page and how many Mb it takes to show one button. But regarding the backend, the vibecoding still rare, and we are still lucky it is like that, and there was no train crush because of it. Yet.

I think you’re onto something. Frontend tends to not actually solve problems, rather it’s mostly hiding and showing parts of a page. Sometimes frontend makes something possible that wasn’t possible before, and sometimes the frontend is the product, but usually the frontend is an optimization that makes something more efficient, and the problem is being solved on the backend. It’s been interesting to observe when peop…

Spoken like someone deeply unfamiliar with the problem domain since like 2005, sorry. It's an entirely different class of problems on the front end, most of them dealing with making users happy and comfortable, which is much more challenging than any of the rote byte pushing happening on the backend nowadays.

Re: ChatGPT Containers can now run bash, pip/npm install packages and download files

#193

Post by fooker »

jacquesm wrote: post #189
fooker wrote: post #159

Earlier quoted context omitted.

I have worked on some of the most supposedly reliable codebases on earth (compilers) for several decades, and most of the code in compilers is pretty bad. And most of the code the compiler is expected to compile, seen from the perspective of fixing bugs and issues with compilers, is absolutely terrible. And the day that can be rewritten or improved reliably with AI can't come fast enough.

I honestly do not see how training AI on 'mountains of garbage' would have any other outcome than more garbage. I've seen lots of different codebases from the inside, some good some bad. As a rule smaller + small team = better and bigger + more participants = worse.

The way it seems to work now is to task agents to write a good test suite. AI is much better at this than it is at writing code from scratch.

Then you just let it iterate until tests pass. If you are not happy with the design, suggest a newer design and let it rip.

All this is expensive and wasteful now, but stuff becoming 100-1000x cheaper has happened for every technology we have invented.

Re: ChatGPT Containers can now run bash, pip/npm install packages and download files

#194

Post by fooker »

simonw wrote: post #191
jacquesm wrote: post #189

Earlier quoted context omitted.

I honestly do not see how training AI on 'mountains of garbage' would have any other outcome than more garbage. I've seen lots of different codebases from the inside, some good some bad. As a rule smaller + small team = better and bigger + more participants = worse.

That's why the major AI labs are really careful about the code they include in the training runs. The days of indiscriminately scraping every scrap of code on the internet and pumping it all in are long gone, from what I can tell.

Do you have pointers to this?

Would be a great resource to understand what works and what doesn't.

Re: ChatGPT Containers can now run bash, pip/npm install packages and download files

#195

Post by llbbdd »

zx8080 wrote: post #145
cheeze wrote: post #132

Earlier quoted context omitted.

FAANG here (service oriented arch, distributed systems) and id say probably 20+ percent of code written on my team is by an LLM. it's great for frontends, works well with test generation, or following an existing paradigm. I think a lot of people wrote it off initially as it was low quality. But gemini 3 pro or sonnet 4.5 saves me a ton of time at work these days. Perfect? Absolutely not. Good enough for tons of run…

> probably 20+ percent of code written on my team is by an LLM. it's great for frontends Frontend has always been shitshow since JS dynamic web UIs invented. With it and CSS no one cares what runs page and how many Mb it takes to show one button. But regarding the backend, the vibecoding still rare, and we are still lucky it is like that, and there was no train crush because of it. Yet.

Backend has always been easier than frontend. AI has made backend absolutely trivial, the code only has to work on one type of machine in one environment. If you think it's rare or will remain rare you're just not being exposed to it, because it's on the backend.

Re: ChatGPT Containers can now run bash, pip/npm install packages and download files

#196

Post by paulddraper »

behnamoh wrote: post #5

I wonder if the era of dynamic programming languages is over. Python/JS/Ruby/etc. were good tradeoffs when developer time mattered. But now that most code is written by LLMs, it's as "hard" for the LLM to write Python as it is to write Rust/Go (assuming enough training data on the language ofc; LLMs still can't write Gleam/Janet/CommonLisp/etc.). Esp. with Go's quick compile time, I can see myself using it more and m…

Agreed. The compiler is a feedback cycle made in heaven.

Re: ChatGPT Containers can now run bash, pip/npm install packages and download files

#197

Post by ekianjo »

behnamoh wrote: post #5

I wonder if the era of dynamic programming languages is over. Python/JS/Ruby/etc. were good tradeoffs when developer time mattered. But now that most code is written by LLMs, it's as "hard" for the LLM to write Python as it is to write Rust/Go (assuming enough training data on the language ofc; LLMs still can't write Gleam/Janet/CommonLisp/etc.). Esp. with Go's quick compile time, I can see myself using it more and m…

Still less tokens to produce with higher level languages, and therefore less cost to maintain in the long run?

Re: ChatGPT Containers can now run bash, pip/npm install packages and download files

#198

Post by bopbopbop7 »

llbbdd wrote: post #195
zx8080 wrote: post #145

Earlier quoted context omitted.

> probably 20+ percent of code written on my team is by an LLM. it's great for frontends Frontend has always been shitshow since JS dynamic web UIs invented. With it and CSS no one cares what runs page and how many Mb it takes to show one button. But regarding the backend, the vibecoding still rare, and we are still lucky it is like that, and there was no train crush because of it. Yet.

Backend has always been easier than frontend. AI has made backend absolutely trivial, the code only has to work on one type of machine in one environment. If you think it's rare or will remain rare you're just not being exposed to it, because it's on the backend.

Might be a surprise to you, but some backends are more than just a Nextjs endpoint that calls a database.

Re: ChatGPT Containers can now run bash, pip/npm install packages and download files

#199

Post by throwaway2027 »

jmacd wrote: post #3

I wonder how long npm/pip etc even makes sense. Dependancies introduce unnecessary LOC and features which are, more and more, just written by LLMs themselves. It is easier to just write the necessary functionality directly. Whether that is more maintainable or not is a bit YMMV at this stage, but I would wager it is improving.

That was already the case for a lot of things like is-even.

Re: ChatGPT Containers can now run bash, pip/npm install packages and download files

#200

Post by ford »

jmacd wrote: post #3

I wonder how long npm/pip etc even makes sense. Dependancies introduce unnecessary LOC and features which are, more and more, just written by LLMs themselves. It is easier to just write the necessary functionality directly. Whether that is more maintainable or not is a bit YMMV at this stage, but I would wager it is improving.

Interesting thought (I think recently more than ever it's a good idea to question assumptions) - but IMO abstractions are important as ever.

Maybe the smallest/most convenient packages (looking at you is-even) are obsolete, but meaningful packages still abstract a lot of complexity that IMO aren't easier to one-shot with an LLM

Post reply on HN