Live data from Hacker News

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

simonwillison.net

61–70 of 336 posts

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

#61
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.

At times I wonder why x tui coding agent was written in js/ts/python, why not use Go if it's mostly llm coded anyway? But that's mostly my frustration at having to wait for npm to install a thousand dependencies, instead of one executable plus some config files. There's also support libraries like terminal ui that differ in quality between platforms.

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

#62
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 think you're missing the reason LLMs work: It's cause they can continue predictable structures, like a human.

The surmise that compiled languages fit that just doesn't follow. The same way LLMs have trouble finishing HTML because of the open/close are too far apart.

The language that an LLM would succeed with is one where:

1. Context is not far apart

2. The training corpus is wide

3. Keywords, variables, etc are differentiated in the training.

4. REPL like interactivity allows for a feedback loop.

So, I think it's premature to think just because the compiled languages are less used because of human inabilities, doesn't mean the LLM will do any better.

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

#65
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).

I want to create a language that allows an LLM to dynamically decide what to do.

A non dertermistic programing language, which options to drop down into JavaScript or even C if you need to specify certain behaviors.

I'd need to be much better at this though.

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

#66
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).

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 training process harder. Even worse, say you get a year and 500 features into that repo and the LLM starts going rogue - who's gonna debug that?

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

#67
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.

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

#68
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).

Most programming languages are great for LLMs. The problem is with the natural language specification for architectures and tasks. https://brannn.github.io/simplex/

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

#70
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.

best to write assembly instead.
Post reply on HN