Live data from Hacker News

Cowork: Claude Code for the rest of your work

claude.com

231–240 of 593 posts

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

#231
post #182

I wrote up some first impressions of Claude Cowork here, including an example of it achieving a task for me (find the longest drafts in my blog-drafts folder from the past three months that I haven't published yet) with screenshots. https://simonwillison.net/2026/Jan/12/claude-cowork/

I tend to think this product is hard for those of us who've been using `claude` for a few months to evaluate. All I have seen and done so far with Cowork are things _I_ would prefer to do with the terminal, but for many people this might be their first taste of actually agentic workflows. Sometimes I wonder if Anthropic sort of regret releasing Claude Code in its 'runs your stuff on your computer' form - it can quite…

Claude Cowork is effectively Claude Code with a less intimidating UI and a default filesystem sandbox. That's a pretty great product for people who aren't terminal nerds!

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

#232
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:…

The first version is for macOS, which has snapshots [1] and file versioning [2] built-in. [1]: https://eclecticlight.co/2024/04/08/apfs-snapshots/ [2]: https://eclecticlight.co/2021/09/04/explainer-the-macos-vers...

Are average users likely to be using these features? Most devs at my company don’t even have Time Machine backups

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

#233
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-…

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?

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

#234
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.

I send my bank statements to Gemini to analyze. It's not like bank statements contain anything too sensitive.

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

#235

Earlier quoted context omitted.

What percentage of non-IT professionals know what zfs/lvm are let alone how to use them to make snapshots?

I assumed we are talking about IT professionals using tools like claude here? But even for normal people it's not really hard if they manage to leave the cage in their head behind that is ms windows. My father is 77 now and only started using computer abover age 60, never touched windows thanks to me, and has absolutely no problems using (and administrating at this point) it all by himself

This tool is aimed towards consumers, not devs

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

#237
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-…

That's why I run it inside a sandbox - https://github.com/ashishb/amazing-sandbox

Dagger also made something: https://github.com/dagger/container-use

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

#238
post #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.

Related: https://news.ycombinator.com/item?id=46594059

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

#239
post #231

Earlier quoted context omitted.

I tend to think this product is hard for those of us who've been using `claude` for a few months to evaluate. All I have seen and done so far with Cowork are things _I_ would prefer to do with the terminal, but for many people this might be their first taste of actually agentic workflows. Sometimes I wonder if Anthropic sort of regret releasing Claude Code in its 'runs your stuff on your computer' form - it can quite…

Claude Cowork is effectively Claude Code with a less intimidating UI and a default filesystem sandbox. That's a pretty great product for people who aren't terminal nerds!

I agree!

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

#240
Anthropic blog posts have always caused a blank page for me, so I had Claude Code dig into it using an 11 MB HAR of a session that reproduces the problem, and it used grep and sed(!) to find the issue in just under 5 minutes (4m56s).

Turns out that the data-prevent-flicker attribute is never removed if the Intellimize script fails to load. I use DNS-based adblock and I can confirm that allowlisting api.intellimize.co solves the problem, but it would be great if this could be fixed for good, and I hope this helps.

Post reply on HN