zlacker

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

submitted by simonw+(OP) on 2026-01-26 19:19:40 | 450 points 320 comments
[view article] [source] [go to bottom]

NOTE: showing posts with links only show all posts
◧◩
11. simonw+Mn[view] [source] [discussion] 2026-01-26 21:19:49
>>candid+Bj
Claude Code for the web is kind of a persistent virtual dev environment already.

You can start a session there and chat with it to get a bunch of work done, then come back to that session a day later and the virtual filesystem is in the same state as when you left it.

I haven't figured out if this has a time limit on it - it's possible they're doing something clever with object storage such that the cost of persisting those environments is really low, see also Fly's Sprites.dev: https://fly.io/blog/design-and-implementation/

◧◩
25. Imusta+ss[view] [source] [discussion] 2026-01-26 21:44:34
>>behnam+sj
I love golang man! And I use it for the same thing too!!

I mean people mention rust and everything and how AI can write proper rust code with linter and some other thing but man trust me that AI can write some pretty good golang code.

I mean though, I don't want everyone to write golang code with AI of all of a sudden because I have been doing it for over an year and its something that I vibe with and its my personal style. I would lose some points of uniqueness if everyone starts doing the same haha!

Man my love for golang runs deep. Its simple, cross platform (usually) and compiles super fast. I "vibe code" but feel faith that I can always manage the code back.

(self promotion? sorry about that: but created golang single main.go file project with a timer/pomodoro with websockets using gorilla (single dep) https://spocklet-pomodo.hf.space/)

So Shhh let's keep it a secret between us shall we! ;)

(Oh yeah! Recently created a WHMCS alternative written in golang to hook up to any podman/gvisor instance to build your own mini vps with my own tmate server, lots of glue code but it actually generated it in first try! It's surprisingly good, I will try to release it as open source & thinking of charging just once if people want everything set up or something custom

Though one minor nitpick is that the complexity almost rises many folds between a single file project and anything which requires database in golang from what I feel usually but golang's pretty simple and I just LOVE golang.)

Also AI's pretty good at niche languages too I tried to vibe code a fzf alternative from golang to v-lang and I found the results to be really promising too!

◧◩
31. simonw+Zt[view] [source] [discussion] 2026-01-26 21:52:21
>>xnx+Ks
That might work! You would have to figure out how to get Whisper working in there but I'm sure that's possible with a bit of creativity concerning uploading files and maybe running a build with the available C compiler.

It appears to have 4GB of RAM and 56 (!?) CPU cores https://chatgpt.com/share/6977e1f8-0f94-8006-9973-e9fab6d244...

◧◩◪
43. simonw+ew[view] [source] [discussion] 2026-01-26 22:03:48
>>kenjac+Uv
There was an interesting effort in that direction the other day: https://simonwillison.net/2026/Jan/19/nanolang/
◧◩◪◨⬒⬓
52. simonw+0A[view] [source] [discussion] 2026-01-26 22:27:24
>>Imusta+Cw
On my free ChatGPT account I ran a prompt telling it to write and execute hello world in a bunch of languages: https://chatgpt.com/share/6977aa7c-7bd8-8006-8129-8c9e25126f...

It did what I asked - proving that the container feature works even for free accounts - but then displayed a message saying that I was as out of free prompts and would need to upgrade or wait before I could run more.

◧◩
54. tintor+mB[view] [source] [discussion] 2026-01-26 22:32:19
>>nottor+qr
No root. `pip` and `npm install` don't require it.

You can not use `sudo apt install` inside it.

They use gVisor, and other container isolation mechanisms: https://ryan.govost.es/2025/openai-code-interpreter/

◧◩◪
65. branaf+BK[view] [source] [discussion] 2026-01-26 23:18:22
>>kenjac+Uv
Most programming languages are great for LLMs. The problem is with the natural language specification for architectures and tasks. https://brannn.github.io/simplex/
◧◩◪
73. skybri+MM[view] [source] [discussion] 2026-01-26 23:32:08
>>simonw+jp
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 Incorrect or missing password.
  npm error If you were trying to login, change your password, create an
  npm error authentication token or enable two-factor authentication then
  npm error that means you likely typed your password in incorrectly.
  npm error Please try again, or recover your password at:
  npm error   https://www.npmjs.com/forgot
  npm error
  npm error If you were doing some other operation then your saved credentials are
  npm error probably out of date. To correct this please try logging in again with:
  npm error   npm login
  npm error A complete log of this run can be found in: /home/oai/.npm/_logs/2026-01-26T21_20_00_322Z-debug-0.log
> Checking and overriding npm registry > It seems like the registry option is protected, possibly pointing to an internal OpenAI registry that requires authentication. To bypass this, I can override the registry in the command with npm i cowsay --registry=https://registry.npmjs.org/. Let's give this a try and see if it works.

It's unclear if that helped.

I tried again and it worked. It seems like I have to ask for it to do things "in the container" or it will just give me directions about how to do it.

◧◩
88. simonw+oR[view] [source] [discussion] 2026-01-26 23:58:41
>>LowLev+nQ
It's one of the tools that are available to ChatGPT - they're not MCP tools because ChatGPT's implementation of tools pre-dates MCP, but they work effectively the same way.

Here's a full list which looks accurate to me: https://chatgpt.com/share/6977ffa0-df14-8006-9647-2b8c90ccbb...

◧◩◪◨⬒⬓
109. branaf+RX[view] [source] [discussion] 2026-01-27 00:43:56
>>999900+ZR
The most accessible way to start experimenting would be the Ralph loop: https://github.com/anthropics/claude-code/tree/main/plugins/...

You could also work backwards from this paper: https://arxiv.org/abs/2512.18470

◧◩
113. jkelle+EY[view] [source] [discussion] 2026-01-27 00:50:53
>>candid+Bj
I started building something for the dioxus team to have access to mac/linux persistent and ephemeral dev envs with vnc and beefy cpu/mem.

Nobody offered multiplatform and we really needed it!

https://skyvm.dev

◧◩
128. lsh0+l21[view] [source] [discussion] 2026-01-27 01:16:19
>>behnam+sj
> LLMs still can't write Gleam/Janet/CommonLisp/etc

hoho - I did a 20/80 human/claude project over the long weekend using Janet: https://git.sr.ht/~lsh-0/pj/tree (dead simple Lerna replacement)

... but I otherwise agree with the sentiment. Go code is so simple it scrubs any creative fingerprints anyway. The Clojure/Janet/scheme code I've seen it writing isn't _great_ but it gets the job done quickly and correct enough for me to return to it later and golf it some.

◧◩◪◨⬒⬓⬔
130. rvz+s31[view] [source] [discussion] 2026-01-27 01:24:49
>>behnam+wT
> The future belongs to generalists!

Couldn't be more correct.

The experienced generalists with techniques of verification testing are the winners [0] in this.

But one thing you cannot do, is openly admit or to be found out to say something like: "I don't know a single line of Rust/Go/Typescript/$LANG code but I used an AI to do all of it" and the system breaks down and you can't fix it.

It would be quite difficult to take a SWE seriously that prides themselves in having zero understanding and experience of building production systems and runs the risk of losing the company time and money.

[0] >>46772520

◧◩
147. 1980ph+G71[view] [source] [discussion] 2026-01-27 01:58:26
>>simonw+d
I was able to install the D language compiler DMD by providing a .deb file.

https://chatgpt.com/share/69781bb5-cf90-800c-8549-c845259c33...

◧◩
165. latexr+6c1[view] [source] [discussion] 2026-01-27 02:34:39
>>tgq291+HF
— Why are you launching nukes? No one asked you to obliterate humanity.

— You’re absolutely right. I should not have done that. Would you like me to help undo the launch?

— Yes! Quickly! Do it!

— <completely made up crap which does not work>

https://www.newyorker.com/cartoon/a16995

◧◩◪
170. simonw+Gd1[view] [source] [discussion] 2026-01-27 02:50:27
>>adw+kd1
Especially since Python 3.14 shipped big improvements to error messages: https://docs.python.org/3/whatsnew/3.14.html#whatsnew314-imp...
◧◩◪◨
171. userna+ug1[view] [source] [discussion] 2026-01-27 03:17:32
>>dankwi+AY
> It's so much faster.

A lot of things are "so much faster" than the right thing. "Vibe traffic safety laws" are much faster than ones that increase actual traffic safety: http://propublica.org/article/trump-artificial-intelligence-... . You, your team, and colleagues are producing shiny trash at unbelievable velocity. Is that valuable?

◧◩◪◨⬒⬓
179. simonw+Ch1[view] [source] [discussion] 2026-01-27 03:28:00
>>trollb+6h1
I had great results recently with ~22 year old PHP: https://simonwillison.net/2025/Jul/1/mid-2000s/

It even guessed the vintage correctly!

> This appears to be a custom template system from the mid-2000s era, designed to separate presentation logic from PHP code while maintaining database connectivity for dynamic content generation.

◧◩
209. naruho+zy1[view] [source] [discussion] 2026-01-27 06:27:54
>>tgq291+HF
Mechahitler[1] now has a job at the Pentagon.[2]

[1] https://www.npr.org/2025/07/09/nx-s1-5462609/grok-elon-musk-...

[2] https://www.bbc.com/news/articles/c628d9mre3go

◧◩
249. useful+Xf2[view] [source] [discussion] 2026-01-27 12:04:23
>>bandra+h91
Hmm...

>>44367548

◧◩◪◨
266. lpcvoi+Ez2[view] [source] [discussion] 2026-01-27 14:10:18
>>darkno+Aw2

  # curl -s https://upload.wikimedia.org/wikipedia/commons/6/61/Sun.png | file -
  /dev/stdin: PNG image data, 256 x 256, 8-bit/color RGBA, non-interlaced
That's it, two utilities almost everybody has installed.
◧◩
274. simonw+MU2[view] [source] [discussion] 2026-01-27 15:40:19
>>e12e+AS2
I got that from the https://chatgpt.com/ web app - I just tried the same prompt in the ChatGPT iPhone app and got the gmail. and gcal. ones too: https://chatgpt.com/share/6978dc20-8a70-8006-9b42-6c0a8080be...

Looks like it's for this feature: https://mashable.com/article/chatgpt-5-openai-gmail-calendar

Presumably you have to opt-in to turning this on somewhere.

◧◩◪◨⬒⬓⬔⧯▣
275. simonw+BV2[view] [source] [discussion] 2026-01-27 15:43:30
>>lpcvoi+FK2
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.)

◧◩
279. indigo+k43[view] [source] [discussion] 2026-01-27 16:19:28
>>candid+Bj
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

◧◩◪◨⬒
280. simonw+Z43[view] [source] [discussion] 2026-01-27 16:22:03
>>antonv+223
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: >>46779522
◧◩◪◨
282. indigo+453[view] [source] [discussion] 2026-01-27 16:22:15
>>simonw+fp
Not ephemeral, but similar idea to keep things isolated in LXC containers. Disclosure, my project.

https://github.com/jgbrwn/vibebin

◧◩◪◨
283. indigo+G53[view] [source] [discussion] 2026-01-27 16:24:13
>>Imusta+xv
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

◧◩
289. 0xbadc+Mm3[view] [source] [discussion] 2026-01-27 17:25:41
>>candid+Bj
That's what GitHub Codespaces is, and it runs Copilot too (it's just a hosted VSCode Web instance specific to your git repo)

Google has Cloud Shell, and Google's AI Studio (https://aistudio.google.com/) gives you a web-based dev environment with Gemini integration

◧◩◪
294. e12e+JB3[view] [source] [discussion] 2026-01-27 18:24:44
>>simonw+MU2
Strange. When logged in to a free account on Android:

https://chatgpt.com/share/697902ad-3070-800d-b523-0fe312c772...

◧◩◪◨⬒
304. simonw+MZ3[view] [source] [discussion] 2026-01-27 19:58:22
>>asadot+KJ3
It turns out if you tell a coding agent "make it accessible" you'll get better results than you would from most professional front-end developers.

I'm not satisfied yet: I want coding agents to be able to actively test on screen readers as part of their iteration loop.

I've not found a system that can do that well yet out of the box, but GuidePup is very promising: https://github.com/guidepup/guidepup

◧◩◪◨⬒⬓⬔⧯
310. llbbdd+QH4[view] [source] [discussion] 2026-01-27 22:52:18
>>Applej+Zs2
If you search Google Trends for enshittification, half the results contain Doctorow as well [0]. Normal people have no idea who that is. And that's just Google, which everyone on HN hates to the point of vibrating angrily because there isn't an obvious part of the name to replace derogatorily with a dollar sign. Nobody uses this term outside of Hacker News, and even on HN it's code for "this site doesn't work when I disable Javascript", which is not a real requirement real customers have.

User experience does involve a lot of subjectivity [1] and that's part of what makes it hard. You have to satisfy the computer and the person in front of it, and their wants are often at odds with each other. You have to make them both happy at 60 FPS minimum.

[0] https://trends.google.com/explore?q=enshittification&date=al...

[1] https://emsh.cat/good-taste/

[go to top]