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

291–300 of 336 posts

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

#291

Post by simonw »

lpcvoid wrote: post #287
simonw wrote: post #286

Earlier quoted context omitted.

"Delegating thinking" and "figuring out how to determine an image format from the first few bytes of a file" are not the same thing.

I disagree, in my opinion it's the exact same process, just on a much smaller scale. It's a problem, and we humans are good at solving problems. That is, until LLMs arrived, now we are supposed to become good at prompting, or something.

I used ffmpeg and yt-dlp to make an animated GIF of a kākāpō in her nest from a livestream on YouTube the other day. https://simonwillison.net/2026/Jan/25/kakapo-cam/

Much as I love kākāpō there is no way I was going to invest more than a few minutes in figuring out how to do that.

I love this new world where I can "delegate my thinking" to a computer and get a GIF of a dumpy New Zealand flightless parrot where I would otherwise be unable to do so because I didn't have the time to figure it out.

(I published it as a looping MP4 because that was smaller than the GIF, another thing I didn't have to figure out how to do myself.)

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

#292

Post by lpcvoid »

simonw wrote: post #291
lpcvoid wrote: post #287

Earlier quoted context omitted.

I disagree, in my opinion it's the exact same process, just on a much smaller scale. It's a problem, and we humans are good at solving problems. That is, until LLMs arrived, now we are supposed to become good at prompting, or something.

I used ffmpeg and yt-dlp to make an animated GIF of a kākāpō in her nest from a livestream on YouTube the other day. https://simonwillison.net/2026/Jan/25/kakapo-cam/ Much as I love kākāpō there is no way I was going to invest more than a few minutes in figuring out how to do that. I love this new world where I can "delegate my thinking" to a computer and get a GIF of a dumpy New Zealand flightless parrot where I wou…

I agree that your project is cool, I just don't think the numerous downsides are worth the occasional cool thing like this.

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

#293

Post by antonvs »

hluska wrote: post #252
PunchyHamster wrote: post #247

Earlier quoted context omitted.

You have insane delusions about how capable LLMs are but even assuming its somehow true : downloading deps instead of hallucinating more code saves you on tokens

And your opinions on how average people use these tools are 100% accurate?

If average people try vibecoding their dependencies, they’ll fail, simple as that. We’ve already seen how that looks with the “web browsers” that have recently been vibecoded.

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

#294

Post by smeej »

As a person who's worked in support roles in tech companies and has a working familiarity with Python but is not a software developer or engineer at all, it's been fascinating to watch the changes.

In the last couple weeks, both Gemini and Claude have asked me, "Can I use the computer?" to answer some particular question. In both cases, my question to each was, "What computer? Mine, or do you have your own?" Here I had thought they were computers, in the vague Star Trek sense. I'm just using the free version in the browser, so I would have been surprised if it had been able to use my computer.

They had their own, and I could watch them script something up in Python to run the calculations I was looking for. It made me wonder who it was at Google/Anthropic who first figured out that the way to get LLMs to stop wetting their metaphorical pants when asked to do calculations was to give them a computer to use.

It did make me scratch my head when I was trying to prompt Nano Banana to generate something and it was like Gemini started talking about the image generator in the third person: "The AI is getting stuck on the earlier instruction, even though we've now abandoned that approach." Felt a little "turtles all the way down" with that one!

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

#295

Post by indigodaddy »

candiddevmike wrote: post #6

Seems like everyone is trying to get ahead of tool calling moving people "off platform" and creating differentiators around what tools are available "locally" to the models etc. This also takes the wind out of the sandboxing folks, as it probably won't be long before the "local" tool calling can effectively do anything you'd need to do on your local machine. I wonder when they'll start offering virtual, persistent de…

I don't know, I've been working on this project [1], and I think efforts around isolating AI coding tool/agents is worthwhile, as most coding people will be using these more focused coding tools vs a vanilla gpt webui.

[1] https://github.com/jgbrwn/vibebin

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

#296

Post by simonw »

antonvs wrote: post #293
hluska wrote: post #252

Earlier quoted context omitted.

And your opinions on how average people use these tools are 100% accurate?

If average people try vibecoding their dependencies, they’ll fail, simple as that. We’ve already seen how that looks with the “web browsers” that have recently been vibecoded.

There's a new web browser project today that's a heck of a lot more impressive than the previous ones - ~20,000 lines of dependency-free Rust (though it uses system libraries for image and text rendering), does a good job of the Hacker News homepage: https://news.ycombinator.com/item?id=46779522

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

#297

Post by antonvs »

abrookewood wrote: post #151
anonzzzies wrote: post #90

Earlier quoted context omitted.

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 a…

Why not get it to write it in Rust in the first place?

Presumably the thought experiment hasn’t matured to that point yet.

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

#298

Post by indigodaddy »

simonw wrote: post #16
yoyohello13 wrote: post #12

Earlier quoted context omitted.

> I wonder when they'll start offering virtual, persistent dev environments... A lot of companies have been wanting to move in this direction. Instead of maintaining a fleet of machines, you just get a bunch of thin clients and pay Microsoft of whoever to host the actual workloads. They already do this 'kiosk' style stuff for a lot of front-line staff. Honestly, not having my own local hardware for development sounds…

Coding agents are a particularly good fit for disposable development environments because of the risk of them messing things up. If the entire environment is ephemeral the worst that can happen (aside from private source code leaks to a malicious third party) is the environment gets trashed and you have to start over in a new one.

Not ephemeral, but similar idea to keep things isolated in LXC containers. Disclosure, my project.

https://github.com/jgbrwn/vibebin

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

#299

Post by indigodaddy »

Imustaskforhelp wrote: post #40
yoyohello13 wrote: post #12

Earlier quoted context omitted.

> I wonder when they'll start offering virtual, persistent dev environments... A lot of companies have been wanting to move in this direction. Instead of maintaining a fleet of machines, you just get a bunch of thin clients and pay Microsoft of whoever to host the actual workloads. They already do this 'kiosk' style stuff for a lot of front-line staff. Honestly, not having my own local hardware for development sounds…

We are gonna have YOLO agents who will deploy directly to website (technically exe.dev already does that for me when I ask it to generate golang projects lol) Honestly I felt like it really bores me or (overwhelms?) me because now I feel like okay now I will do this, then that and then that & drastically expand the scope of the project but that comes with its own fatigue and the limits of free tokens or context with…

I started working in this for if/when I was taxing exe.dev infra and/or running if I ran out of credits (which actually hasn't happened yet):

https://github.com/jgbrwn/vibebin

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

#300

Post by antonvs »

mjevans wrote: post #152
manishsharan wrote: post #143

Earlier quoted context omitted.

If I may ask, does the code produced by LLM follow best practices or patterns? What mental model do you use to understand or comprehend your codebase? Please know that I am asking as I am curious and do not intend to be disrespectful.

Think of the LLM as a slightly lossy compression algorithm fed by various pattern classifiers that weight and bin inputs and outputs. The user of the LLM provides a new input, which might or might not closely match the existing smudged together inputs to produce an output that's in the same general pattern as the outputs which would be expected among the training dataset. We aren't anywhere near general intelligence…

Ignoring your last line, which is poorly defined, this view contradicts observable reality. It can’t explain an LLM’s ability to diagnose bugs in code it hasn’t seen before, exhibit a functional understanding of code it hasn’t seen before, explain what it’s seeing and doing to a human user, etc.

Functionally, on many suitably scoped tasks in areas like coding and mathematics, LLMs are already superintelligent relative to most humans - which may be part of why you’re having difficulty recognizing that.

Post reply on HN