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

321–330 of 336 posts

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

#321

Post by smeej »

kridsdale1 wrote: post #308
smeej wrote: post #294

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 h…

You’re seeing perspectives of the distributed system from inside the system. I’m building multi server multi agent products and they do apparently perceive (anthropomorphizing I know) their connected servers as other people.

Looking at the world, it really makes me wonder if "human" is what we want to model these machines on. It's not obvious to me what else we should choose, but working together peaceably and effectively doesn't seem to be our strongest attribute when writ large.

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

#322

Post by 0xbadcafebee »

simonw wrote: post #307
0xbadcafebee wrote: post #304

This is basically the same functionality as OpenAI Codex Web has, which, if you've not used it, you absolutely should not. What a garbage piece of software. Anthropic is eating OpenAI's lunch.

It's a bit different from Codex Web in that it can't open PRs against projects and can't be configured with internet access. It is better than Codex Web in that you can continue to chat with the agent while it's working - Claude Code for web has that too. Codex Web really needs to catch up there!

Codex Web actually lacks the most basic PR integration, it's so useless. Codex Web refuses to push any binary file to your PR (like images, jars, lock files, etc). It can't check your GH Actions' logs for failures to try to fix them. Replying to one of the PR comments to accept a fix requires replying to a different GitHub bot than the one that opens your PR. And though there's a "Secrets" configuration to add secret vars for a Codex repo, Codex can't access them, so you can't even work around these bugs by asking Codex to make API calls. It's like nobody at the company has tried their own product.

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

#323

Post by fooker »

antonvs wrote: post #317
fooker wrote: post #302

Earlier quoted context omitted.

> 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…

> The cost of LLMs dealing with their own generated multi-million LOC systems is very unlikely to become tractable in the near future

If you have a concrete way to pose this problem, you'll find that there will be concrete solutions.

There is no way to demonstrate something as vague as "resolving the technical debt that it created".

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

#324

Post by Imustaskforhelp »

indigodaddy wrote: post #299
Imustaskforhelp wrote: post #40

Earlier quoted context omitted.

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

Dude I actually followed you on lowendtalk and I already have this project starred :)

Great to see a fellow let user in here xD

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

#325

Post by Imustaskforhelp »

indigodaddy wrote: post #299
Imustaskforhelp wrote: post #40

Earlier quoted context omitted.

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

This is actually a really great project, I actually wanted to build such a project, I don't know if I already said this comment in LET tho but haha yea kudos for making this!

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

#326

Post by llbbdd »

Applejinx wrote: post #273
llbbdd wrote: post #192

Earlier quoted context omitted.

Spoken like someone deeply unfamiliar with the problem domain since like 2005, sorry. It's an entirely different class of problems on the front end, most of them dealing with making users happy and comfortable, which is much more challenging than any of the rote byte pushing happening on the backend nowadays.

Is it, though? That sounds very subjective, and from what I can tell 'enshittification' is a popular user term for the result, so I'm not sure it's going that great.

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/

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

#327

Post by indigodaddy »

Imustaskforhelp wrote: post #325
indigodaddy wrote: post #299

Earlier quoted context omitted.

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

This is actually a really great project, I actually wanted to build such a project, I don't know if I already said this comment in LET tho but haha yea kudos for making this!

Awesome man, it's great to get some positive feedback, appreciate it a lot. I'm actively working on it. Got rid of openhands in favor of Shelley, stuff like that. Stuff that's not tested is like actually taking snapshots thru the TUI, that's there, but didn't actually test/do it yet. Cloudflare API is good but the Desec API feature is there but haven't tested it yet. So I'm sure stuff will come up as more people and I actually start attempting more functionality. The admin.code web UI is neat though where you can start and toggle/choose which coding tool webui is running/listening on 9999 in the container. And also update the AI coding tools thru that webui.

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

#328

Post by indigodaddy »

Imustaskforhelp wrote: post #324
indigodaddy wrote: post #299

Earlier quoted context omitted.

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

Dude I actually followed you on lowendtalk and I already have this project starred :) Great to see a fellow let user in here xD

Ah neat! If you have time throw a comment into the LET post, I'd appreciate it. :)

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

#330

Post by piskov »

martinald wrote: post #117
piskov wrote: post #74

Earlier quoted context omitted.

Shame no c# in that list

Probably (?) not related but there is an issue with claude code for web with nuget. It doesn't support the proxy auth mechanism that anthropic gives it. I wonder if it's the same problem here.

Why do you need auth to download public packages from nuget?
Post reply on HN