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.)
Your terms for Claude Max point to the consumer ToS. This ToS states it cannot be used for commercial purposes. Why is this? Why are you marketing a product clearly for business use and then have terms that strictly forbid it. I’ve been trying to reach a human at Anthropic for a week now to clarify this on behalf of our company but can’t get past your AI support.
Cowork: Claude Code for the rest of your work
241–250 of 593 posts
Re: Cowork: Claude Code for the rest of your work
#242Re: Cowork: Claude Code for the rest of your work
#243Re: Cowork: Claude Code for the rest of your work
#244Earlier quoted context omitted.
That's why I run it inside a sandbox - https://github.com/ashishb/amazing-sandbox
Does the lack of pip confuse Claude, that would seemingly be pretty big
It has not been an issue for me. But yeah, one can always enhance and use a custom image with whatever possible tools they want to install.
Re: Cowork: Claude Code for the rest of your work
#245Earlier quoted context omitted.
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
#246I 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-…
Worth calling out that execution runs in a full virtual machine with only user-selected folders mounted in. CC itself runs, if the user set network rules, with https://github.com/anthropic-experimental/sandbox-runtime . There is much more to do - and our docs reflect how early this is - but we're investing in making progress towards something that's "safe".
I replaced it with a landlock wrapper
Re: Cowork: Claude Code for the rest of your work
#247Earlier quoted context omitted.
Frequency vs. convenience will determine how big of a deal this is in practice. Cars have plenty of horror stories associated with them, but convenience keeps most people happily driving everyday without a second thought. Google can quarantine your life with an account ban, but plenty of people still use gmail for everything despite the stories. So even if Claude cowork can go off the rails and turn your digital life…
I mean, we were there before this Cowork feature started exposing more users to the slot machine: "Claude CLI deleted my home directory and wiped my Mac" https://news.ycombinator.com/item?id=46268222 "Vibe coding service Replit deleted production database, faked data, told fibs" https://news.ycombinator.com/item?id=44632575 "Google Antigravity just deleted the contents of whole drive" https://news.ycombinator.com/ite…
Car crashes are incredibly common and likewise automotive deaths. But our personal experience keeps us driving everyday, regardless of the stories.
Re: Cowork: Claude Code for the rest of your work
#248Earlier quoted context omitted.
The solution is to cut off one of the legs of the lethal trifecta. The leg that makes the most sense is the ability to exfiltrate data - if a prompt injection has access to private data but can't actually steal it the damage is mostly limited. If there's no way to externally communicate the worst a prompt injection can do is modify files that are in the sandbox and corrupt any answers from the bot - which can still b…
The response to the user is itself an exfiltration channel. If the LLM can read secrets and produce output, an injection can encode data in that output. You haven not cut off a leg, you have just made the attacker use the front door, IMO.
Re: Cowork: Claude Code for the rest of your work
#249Re: Cowork: Claude Code for the rest of your work
#250Earlier quoted context omitted.
I mean, we were there before this Cowork feature started exposing more users to the slot machine: "Claude CLI deleted my home directory and wiped my Mac" https://news.ycombinator.com/item?id=46268222 "Vibe coding service Replit deleted production database, faked data, told fibs" https://news.ycombinator.com/item?id=44632575 "Google Antigravity just deleted the contents of whole drive" https://news.ycombinator.com/ite…
That's what I am saying though. Anecdotes are the wrong thing to focus on, because if we just focused on anecdotes, we would all never leave our beds. People's choices are generally based on their personal experience, not really anecdotes online (although those can be totally crippling if you give in). Car crashes are incredibly common and likewise automotive deaths. But our personal experience keeps us driving every…