Live data from Hacker News

Cowork: Claude Code for the rest of your work

claude.com

301–310 of 593 posts

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

#301
post #233

Earlier quoted context omitted.

If you're on Linux, you can run AI agents in Firejail to limit access to certain folders/files.

Looks interesting. How does this compare to a container?

Containers aren't a sandbox:

https://news.ycombinator.com/item?id=46405993

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

#302

Earlier quoted context omitted.

Sorry not related - your blog is awesome. Cool to see you here on HN!

I'm starting to suspect some of these comments might be AI generated and it is all an experiment. guy is the top comment in every other HN thread.

This is the Internet. Everyone here is an AI running in a simulator like the Matrix. How do I know you're not an AI? How do you know I'm not? I could be! Please, just use an em—dash when responding to this comment let me know you're AI.

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

#303

Earlier quoted context omitted.

It works on Linux, Windows, macOS, and BSD. It's not locked to Apple's ecosystem. You can back up directly to local storage, SFTP, S3, Backblaze B2, Azure, Google Cloud, and more. Time Machine is largely limited to local drives or network shares. Restic deduplicates at the chunk level across all snapshots, often achieving better space efficiency than Time Machine's hardlink-based approach. All data is encrypted clien…

Almost all of my backup is around restic, including monitoring of backups (when they fail and when they do not run often enough). It is a very solid setup, with 3 independent backups: local, nearby and far away. Now - it took an awful lot of time to set up (including drinking the wrapper to account for everything). This is advanced IT level. So Time Machine is not for ignorant people, but something everyone can use.…

One works, one loses your data. Oh well.

Guess there's a lot of money to be made wrapping it with a paid GUI

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

#304
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:…

Somewhat related is a concern I have in general as things get more "agentic" and related to the prompt injection concerns; without something like legally bullet-proof contracts, aren't we moving into territory of basically "employing" what could basically be "spies" at all levels from personal (i.e., AI company staff having access to your personal data/prompts/chats) to business/corporate espionage, to domestic and international state level actors who would also love to know what you are working on and what you are thinking/chatting about and maybe what your mental health challenges are that you are working through with an AI chat therapist.

I am not even certain if this issue can be solved since you are sending your prompts and activities to "someone else's computer", but I suspect if it is overlooked or hand-waved as insignificant, there will be a time when open, local models will become useful enough to allow most to jettison cloud AI providers.

I don't know about everyone else, but I am not at all confident in allowing access and sending my data to some AI company that may just do a rug pull once they have an actual virtual version of your mind in a kind of AI replication.

I'll just leave it at that point and not even go into the ramifications of that, e.g., "cybercrimes" being committed by "you", which is really the AI impersonator built based on everything you have told it and provide access to.

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

#305

Earlier quoted context omitted.

It's kind of wild how dangerous these things are and how easily they could slip into your life without you knowing it. Imagine downloading some high-interest document stashes from the web (like the Epstein files), tax guidance, and docs posted to your HOA's Facebook. An attacker could hide a prompt injection attack in the PDFs as white text, or in the middle of a random .txt file that's stuffed with highly grepped wo…

The only truly secure computer is an air gapped computer.

Indeed. I'm somewhat surprised 'simonw still seems to insist the "lethal trifecta" can be overcome. I believe it cannot be fixed without losing all the value you gain from using LLMs in the first place, and that's for fundamental reasons.

(Specifically, code/data or control/data plane distinctions don't exist in reality. Physics does not make that distinction, neither do our brains, nor any fully general system - and LLMs are explicitly meant to be that: fully general.)

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

#306
post #117
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?

Some do, some don't. The reality is there are some of us who truly just don't care. The convenience outweighs the negative. Yesterday I told an agent, "here's my api key and my root password - do it for me". Privacy has long since been dead, but at least for myself opsec for personal work is too.

> Privacy has long since been dead, but at least for myself opsec for personal work is too.

Hacker News in 2026.

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

#308
post #94
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:…

So the future is NixOS for non-technical people?

Yes, and I think we're already seeing that in the general trend of recent linux work toward atomic updates. [bootc](https://developers.redhat.com/articles/2024/09/24/bootc-gett...) based images are getting a ton of traction. [universal blue](https://universal-blue.org/) is probably a better brochure example of how bootc can make systems more resilient without needing to move to declarative nix for the entire system like you do in NixOS. Every "upgrade" is a container deployment, and you can roll back or forward to new images at any time. Parts of the filesystem aren't writeable (which pisses people off who don't understand the benefit) but the advantages for security (isolating more stuff to user space by necessity) and stability (wedged upgrades are almost always recoverable) are totally worth it.

On the user side, I could easily see [systemd-homed](https://fedoramagazine.org/unlocking-the-future-of-user-mana...) evolving into a system that allows snapshotting/roll forward/roll back on encrypted backups of your home dir that can be mounted using systemd-homed to interface with the system for UID/GID etc.

These are just two projects that I happen to be interested in at the moment - there's a pretty big groundswell in Linux atm toward a model that resembles (and honestly even exceeds) what NixOS does in terms of recoverability on upgrade.

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

#309

Earlier quoted context omitted.

HN is now where I get my daily does[1] of apathetic indifference/go with the flow attitude. [1] * dose

Is there a place where you get things that are greater and more noble than apathetic indifference/go with the flow attitude?

The folks at the Qubes OS forum care about security, unlike the vast majority of HN users nowadays:

https://forum.qubes-os.org/

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

#310
I like this idea but really do not want to share my personal data to cloud based LLM vendors.

I have a folder which is controlled by Git, the folder contains various markdown files as my personal knowledge base and work planning files (It's a long story that I have gradually migrate from EverNote->OneNote->Obsidian->plain markdown files + Git), last time I tried to wire a Local LLM API(using LMStudio) to claude code/open code, and use the agent to analyze some documents, but the result is not quite good, either can't find the files or answer quality is bad.

Post reply on HN