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

311–320 of 336 posts

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

#311

Post by e12e »

fassssst wrote: post #309
simonw wrote: post #290

Earlier quoted context omitted.

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.

You can turn those on in the “Apps” settings page. They were previously called Connectors.

Hm... I have a Google drive app [Ed: available for install] - but no Gmail/calendar. Maybe because I'm in Europe?

(Not that I'm super excited about giving chat GPT my emails - on the other hand Gemini is already there (Gmail) I guess...).

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

#312

Post by donkeybeer »

lpcvoid wrote: post #282
darknoon wrote: post #278

Earlier quoted context omitted.

I think you'd find that it's far from "any human" who can do this without looking anything up. I have 15y of dev exp and couldn't do this from memory on the cli. Maybe in c, but less helpful to getting stuff done!

# 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.

Yes but now do the same for every bit of programming tooling, sysadmin configuration / debugging problem and concept out there. With just a few seconds to answer each reply.

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

#313

Post by jimbokun »

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.

It still takes a little bit of time for an LLM to rewrite all the software in existence from scratch.

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

#314

Post by asadotzler »

cheeze wrote: post #132
koe123 wrote: post #130

Earlier quoted context omitted.

> But now that most code is written by LLMs Am I in the Truman show? I don’t think AI has generated even 1% of the code that I run in prod, nor does anyone I respect. Heavily inspired by AI examples, heavily assisted by AI during research sure. Who are these devs that are seeing such great success vibecoding? Vibecoding in prod seems irresponsible at best

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…

Does great for front ends mean considerate A11Y? In the projects I've looked over, that's almost never the case and the A11Y implementation is hardly worthy of being called prototype, much less production. Mock up seems to be the best label. I'll bet you think because the surface looks right that runs down to the roots so you call it good at front ends. This is the problem with LLMs, they do not do the hard work and they teach people that the hard work they cannot do is fine left undone or partially done and the more people "program" like this the worse the situation gets for real human beings trying to live in a world dominated by software.

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

#315

Post by jtbayly »

storystarling wrote: post #234
dangoodmanUT wrote: post #133

Giving agents linux has compounding benefits in our experience. They're able to sort through weirdness that normal tooling wouldn't allow. Like they can read and image, get an error back from the API and see it wasn't the expected format. They read the magic bytes to see it was a jpeg despite being named .png, and read it correctly.

Matches my experience with print-on-demand workflows. I tried using vision models to validate things like ICC profiles and total ink density, but they usually just hallucinate that the file is compliant. I ended up giving the agent access to ImageMagick to run analysis directly. It’s the only reliable way to catch issues before sending files to fulfillment, otherwise you end up eating the cost of failed prints.

I don’t understand why you’d try to use an LLM for that step if there is already a tool that you can call to check it. Help me out.

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

#316

Post by blobbers »

aryehof wrote: post #236
blobbers wrote: post #77

Did I miss the boat on chatgpt? Is there something more to it than the web chat interface? I jumped on the Claude Code bandwagon and I dropped off chatgpt. I find the chatgpt voice interface to be infuriating; it literally talks in circles and just spews summary garbage whenever I ask it anything remotely specific.

Chatgpt recently added additional personalization options that have made their voice chat better for me. I want a direct professional, no “hey” there I’m your bro fake stuff etc. See personalization under settings.

Okay, I'll try that out. I was asking it to do something like summarize a balance sheet over a few years and while the chat interface will do this, the voice interface would just tell me to go look up the specific data source, it refused to barf out numbers.

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

#317

Post by antonvs »

fooker wrote: post #302
antonvs wrote: post #301

Earlier quoted context omitted.

I’ve seen those quadrants too, because I’ve come into several companies to help clean up a mess they’ve gotten into with bad code that they can no longer ignore. It is a compete certainty that we’re going to start seeing a lot more of that. One ironic thing about LLM-generated bad code is that churning out millions of lines just makes it less likely the LLM is going to be able to manage the results, because token cap…

> because token capacity is neither unlimited nor free. This is like dissing software from 2004 because it used 2gb extra memory. In the last year, token context window increased by about 100x and halved in cost at the same time. If this is the crux of your argument, technology advancement will render it moot.

> In the last year, token context window increased by about 100x and halved in cost at the same time.

So? It's nowhere close to solving the issue.

I'm not anti-LLM. I'm very senior at a company that's had an AI-centric primary product since before the GPT explosion. But in order to navigate what's going on now, we need to understand the strengths and weaknesses of the technology currently, as well as what it's likely to be in the near, medium, and far future.

The cost of LLMs dealing with their own generated multi-million LOC systems is very unlikely to become tractable in the near future, and possibly not even medium-term. Besides, no-one has yet demonstrated an LLM-based system for even achieving that, i.e. resolving the technical debt that it created.

Don't let fanboism get in the way of rationality.

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

#318

Post by hex4def6 »

lpcvoid wrote: post #272
dangoodmanUT wrote: post #133

Giving agents linux has compounding benefits in our experience. They're able to sort through weirdness that normal tooling wouldn't allow. Like they can read and image, get an error back from the API and see it wasn't the expected format. They read the magic bytes to see it was a jpeg despite being named .png, and read it correctly.

I don't understand why this is something special that somebody would need some LLM slop generation for? Any human can also do this in a few seconds using normal unix tooling.

That's like saying 'why give people calculators, when you can pull out a slide rule'

The whole point is that you are enabling the LLM through tool use. The prompt might be "Download all the images on the wikipedia article for 'Ascetic', and print them on my dot matrix printer (the driver of which only accepts BMPs, so convert as needed)"

Your solution using file / curl is just one part of the potential higher level problem statement. Yes, someone could write those lines easily. And they could write the wrapper around them with only a little more difficulty. And they could add the 404 logic detection with a bit more...

Are you arguing LLMs should only be used on 'hard' problems, and 'easy' problems (such as downloading with curl) should be done by humans? Or are you arguing LLMs should not be used for anything?

Because I think most people would suggest humans tackle the 'hard' problems, and let the tools (LLMs) tackle the 'easy' ones.

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

#320

Post by simonw »

asadotzler wrote: post #314
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…

Does great for front ends mean considerate A11Y? In the projects I've looked over, that's almost never the case and the A11Y implementation is hardly worthy of being called prototype, much less production. Mock up seems to be the best label. I'll bet you think because the surface looks right that runs down to the roots so you call it good at front ends. This is the problem with LLMs, they do not do the hard work and…

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

Post reply on HN