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

81–90 of 336 posts

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

#81

Post by reitzensteinm »

Sheeny96 wrote: post #66
kenjackson wrote: post #44

Earlier quoted context omitted.

Has anyone tried creating a language that would be good for LLMs? I feel like what would be good for LLMs might not be the same thing that is good for humans (but I have no evidence or data to support this, just a hunch).

The problem with this is the reason LLMs are so good at writing Python/Java/JavaScript is that they've been trained on a metric ton of code in those languages, have seen the good the bad and the ugly and been tuned to the good. A new language would be training from scratch and if we're introducing new paradigms that are 'good for LLMs but bad for humans' means humans will struggle to write good code in it, making the…

But coding is largely trained on synthetic data.

For example, Claude can fluently generate Bevy code as of the training cutoff date, and there's no way there's enough training data on the web to explain this. There's an agent somewhere in a compile test loop generating Bevy examples.

A custom LLM language could have fine grained fuzzing, mocking, concurrent calling, memoization and other features that allow LLMs to generate and debug synthetic code more effectively.

If that works, there's a pathway to a novel language having higher quality training data than even Python.

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

#82

Post by simonw »

skybrian wrote: post #76
simonw wrote: post #17

Earlier quoted context omitted.

Can you share the transcript?

https://chatgpt.com/share/6977f9d7-ca94-8000-b1a0-8b1a994e58... The transcript doesn't show it (I think it faked it) but here's the code in the sidebar: > bash -lc mkdir -p /mnt/data/cowsay-demo && cd /mnt/data/cowsay-demo && npm init -y >/dev/null && npm i cowsay@latest >/dev/null && echo 'Installed cowsay version:' && node -e "console.log(require('cowsay/package.json').version)" npm error code E401 npm error Incorr…

OK that's really weird. Intermittent environment bug perhaps?

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

#83

Post by fooker »

jacquesm wrote: post #67
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…

> But now that most code is written by LLMs Is this true? It seems to be a massive assumption.

By lines of code, almost by an order of magnitude.

Some of the code is janky garbage, but that’s what most code it. There’s no use pearl clutching.

Human engineering time is better spent at figuring out which problems to solve than typing code token by token.

Identifying what to work on, and why, is a great research skill to have and I’m glad we are getting to realistic technology to make that a baseline skill.

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

#84

Post by JumpCrisscross »

bogtog wrote: post #78
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…

> 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 The LLM still benefits from the abstraction provided by Python (fewer tokens and less cognitive load). I could see a pipeline working where one model writes in Python or so, then another model is tasked to compile it into a more performant language

NP (as in P = NP) is also much lower for Python than Rust on the human side.

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

#85

Post by jacquesm »

fooker wrote: post #83
jacquesm wrote: post #67

Earlier quoted context omitted.

> But now that most code is written by LLMs Is this true? It seems to be a massive assumption.

By lines of code, almost by an order of magnitude. Some of the code is janky garbage, but that’s what most code it. There’s no use pearl clutching. Human engineering time is better spent at figuring out which problems to solve than typing code token by token. Identifying what to work on, and why, is a great research skill to have and I’m glad we are getting to realistic technology to make that a baseline skill.

Well, you will somehow have to turn that 'janky garbage' into quality code, who will do that then?

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

#86

Post by sakesun »

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…

LLM should generate to terse and easy to read language for human to review. Beside Python, F# can be a perfect fit.

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

#87

Post by voxleone »

kenjackson wrote: post #44
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…

Has anyone tried creating a language that would be good for LLMs? I feel like what would be good for LLMs might not be the same thing that is good for humans (but I have no evidence or data to support this, just a hunch).

>Has anyone tried creating a language that would be good for LLMs?

I’ve thought about this and arrived at a rough sketch.

The first principle is that models like ChatGPT do not execute programs; they transform context. Because of that, a language designed specifically for LLMs would likely not be imperative (do X, then Y), state-mutating, or instruction-step driven. Instead, it would be declarative and context-transforming, with its primary operation being the propagation of semantic constraints. The core abstraction in such a language would be the context, not the variable. In conventional programming languages, variables hold values and functions map inputs to outputs. In a ChatGPT-native language, the context itself would be the primary object, continuously reshaped by constraints. The atomic unit would therefore be a semantic constraint, not a value or instruction.

An important consequence of this is that types would be semantic rather than numeric or structural. Instead of types like number, string, bool, you might have types such as explanation, argument, analogy, counterexample, formal_definition.

These types would constrain what kind of text may follow, rather than how data is stored or laid out in memory. In other words, the language would shape meaning and allowable continuations, not execution paths. An example:

@iterate: refine explanation until clarity ≥ expert_threshold

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

#89

Post by felixgallo »

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…

I wouldn't speak so quickly for the 'uncommon' language set. I had Claude write me a fully functional typed erlang compiler with ocaml and LLVM IR over the last two days to test some ideas. I don't know ocaml. It made the right calls about erlang, and the result passes a fairly serious test suite, so it must've known enough ocaml and LLVM IR.

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

#90

Post by anonzzzies »

bogtog wrote: post #78
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…

> 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 The LLM still benefits from the abstraction provided by Python (fewer tokens and less cognitive load). I could see a pipeline working where one model writes in Python or so, then another model is tasked to compile it into a more performant language

It's very good (in our experience, YMMV of course) when/llm write prototype with python and then port automatically 1-1 to Rust for perf. We write prototypes in JS and Python and then it gets auto ported to Rust and we have been doing this for about 1 year for all our projects where it makes sense; in the past months it has been incredibly good with claude code; it is absolutely automatic; we run it in a loop until all (many handwritten in the original language) tests succeed.
Post reply on HN