Live data from Hacker News

Cowork: Claude Code for the rest of your work

claude.com

201–210 of 593 posts

Re: Cowork: Claude Code for the rest of your work

#201
post #24

I was hoping for a moment that this meant they had come up with a design that was safe against lethal trifecta / prompt injection attacks, maybe by running everything in a tight sandbox and shutting down any exfiltration vectors that could be used by a malicious prompt attack to steal data. Sadly they haven't completely solved that yet. Instead their help page at https://support.claude.com/en/articles/13364135-using-…

I built https://github.com/nezhar/claude-container for exactly this reason - it's easy to make mistakes with these agents even for technical users, especially in yolo mode.

Re: Cowork: Claude Code for the rest of your work

#202
post #36

It's so important to remember that unlike code which can be reverted - most file system and application operations cannot. There's no sandboxing snapshot in revision history, rollbacks, or anything. I expect to see many stories from parents, non-technical colleagues, and students who irreparably ruined their computer. Edit: most comments are focused on pointing out that version control & file system snapshot exists:…

There was a couple of posts here on hacker news praising agents because, it seems, they are really good at being a sysadmin. You don't need to be a non-technical user to be utterly fucked by AI.

Re: Cowork: Claude Code for the rest of your work

#203

Earlier quoted context omitted.

Q: What would prevent them from using git style version control under the hood? User doesn’t have to understand git, Claude can use it for its own purposes.

You can’t easily snapshot the current state of an OS and restore to that state like with git.

I wonder if in the long run this will lead to the ascent of NixOS. They seem perfect for each other: if you have git and/or a snapshotting filesystem, together with the entire system state being downstram of your .nix file, then go ahead and let the LLM make changes willy-nilly, you can always roll back to a known good version.

NixOS still isn't ready for this world, but if it becomes the natural counterpart to LLM OS tooling, maybe that will speed up development.

Re: Cowork: Claude Code for the rest of your work

#204

Hi, Felix from the team here, this is my product - let us know what you think. We're on purpose releasing this very early, we expect to rapidly iterate on it. (We're also battling an unrelated Opus 4.5 inference incident right now, so you might not see Cowork in your client right away.)

Please give me access via api key

Re: Cowork: Claude Code for the rest of your work

#205
post #79

Is there anything similar to this in the local world? I’m setting up a full local “ai” stack on a 48gb MacBook for my sensitive data ops. Using webui. Will still use sota cloud services for coding.

There are lots of similar tools to Claude Code where a local executor agent talks to a remote/local AI. For example, OpenCode and Aider both support local models as well as remote (e.g. via OpenRouter).

Yes, I have that working via Roo Code in VS code. Doing a little searching I found this which looks promising: https://github.com/hyperfield/ai-file-sorter

Re: Cowork: Claude Code for the rest of your work

#206
post #26

People do realize that if they're doing this, they're not feeding "just" code into some probably logging cloud API but literally anything (including, as mentioned here, bank statements), right? Right? RIGHT?????? Are you sure that you need to grant the cloud full access to your desktop + all of its content to sort elements alphabetically?

I have my bank statements on a drive on a cloud. We are way past that phase.

Re: Cowork: Claude Code for the rest of your work

#208
post #166

I'm a bit shocked to see so many negative comments here on HN. Yes, there are security risks and all but honestly this is the future. It's a great amplifier for hackers and people who want to get stuff done. It took some training but I'm now starting almost all tasks with claude code: need to fill out some word document, organize my mail inbox, write code, migrate blog posts from one system to another, clean up my co…

So people shouldn't say their opinion because your opinion says its the future? Is all future good? I don't think a great hacker would struggle to organise their desktop or they will waste their team's time with AI generated deck but no one can stop others from using it.

Re: Cowork: Claude Code for the rest of your work

#209

Earlier quoted context omitted.

> (I don't think it's fair to ask non-technical users to look out for "suspicious actions that may indicate prompt injection" personally!) It's the "don't click on suspicious links" of the LLM world and will be just as effective. It's the system they built that should prevent those being harmful, in both cases.

Operating systems should prevent privilege escalations, antiviruses should detect viruses, police should catch criminals, claude should detect prompt injections, ponies should vomit rainbows.

I believe the detection pattern may not be the best choice in this situation, as a single miss could result in significant damage.

Re: Cowork: Claude Code for the rest of your work

#210
post #36

It's so important to remember that unlike code which can be reverted - most file system and application operations cannot. There's no sandboxing snapshot in revision history, rollbacks, or anything. I expect to see many stories from parents, non-technical colleagues, and students who irreparably ruined their computer. Edit: most comments are focused on pointing out that version control & file system snapshot exists:…

Q: What would prevent them from using git style version control under the hood? User doesn’t have to understand git, Claude can use it for its own purposes.

Git only works for text files. Everything else is a binary blob which, among other things, leads to merge conflicts, storage explosion, and slow git operations
Post reply on HN