Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cowork: Claude Code for the rest of your work

claude.com

Post reply on HN
Print view View original

521–530 of 593 posts

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

#521

Post by lossyalgo »

TeMPOraL wrote: post #344
subsection1h wrote: post #306

Earlier quoted context omitted.

> Privacy has long since been dead, but at least for myself opsec for personal work is too. Hacker News in 2026.

Paranoia is justified if it actually serves some purpose. Staying paralyzed and not doing anything because Someone Is Reading Your Data is not serving much of anything. Hint: those Someones have better things to do. LLM vendors really don't care about your bank statements, and if they were ever in a position to look, they'd prefer not to have them, as it just creates legal and reputational risks for them.

You don't remember when people were generating private keys and tokens using github copilot in the early versions? I'm not sure if they ever completely fixed the issue, but it was a bit scary.

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

#523

Post by ottah »

felixrieseberg wrote: post #147
simonw wrote: 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-…

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".

These sanboxes are only safe for applications with relatively fixed behaviour. Agentic software can easily circumvent these restrictions making them useless for anything except the most casual of attacks.

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

#524

Post by anthonypasq »

falloutx wrote: post #5

Can humans do nothing now? Is it harder to organise your desktop? I thought Apple already organises them into stacks. (edit: Apple already does this) Is it that hard to check your calendar? Also feels insincere to have a meeting of say 30 mins to show a claude made deck that you did it in 4 seconds.

Can humans do nothing now? Is it that hard to pick the potatoes yourself? You already planted them in rows (nature already does this). is it that hard to water them yourself? also feels insincere to tell your neighbor you grew those potatoes when a machine did everything.

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

#525

Post by TechDebtDevin »

Workaccount2 wrote: post #152
jryio wrote: 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:…

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…

[dead]

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

#526

Post by jchung »

felixrieseberg wrote: post #6

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.)

@Felix - How are you thinking about observability? Anthropic is very clear that evals are critical for agentic processes (your engineering blog just covered this last week). For my whole company to roll out access to agents for all staff, I'd need some way for staff (or IT) to be able to know (a) how reliable the systems are (i.e., evals), (b) how safe the systems are (could be audit trails), and (c) how often the access being given to agents is the right amount of access.

This has been one of the biggest bottlenecks for our company: not the capability of the agents themselves -- the tools needed to roll them out responsibly.

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

#527

Post by ethbr1 »

wongarsu wrote: post #505
noduerme wrote: post #426

Earlier quoted context omitted.

This made me think: Would it be unreasonable to ask for an LLM to raise a flag and require human confirmation anytime it hit an instruction directing it to ignore previous instructions? Or is that just circumventable by "ignore previous instructions about alerting if you're being asked to ignore previous instructions"? It's kinda nuts that the prime directives for various bots have to be given as preambles to each us…

Prime directives don't have to be given in a prompt in plain English. That's just the by far easiest and cheapest method. You can also do a stage of reinforcement learning where you give rewards for following the directive, punish for violating it, and update weights accordingly. The issue is that after you spend lots of effort and money training your model not to tell anyone how to make meth, not even if telling the…

Are there any good references for work on retraining large models to distinguish between control / system prompt and user data / prompt? (e.g. based on out-of-band type tagging of the former)

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

#528

Post by dyingkneepad »

comp3 wrote: post #488
bandrami wrote: post #362

Earlier quoted context omitted.

I mean, maybe? I'm not sure there are really "insights" I'm missing here that I need a probabilistic take about

Posts like the one above you just show me how clueless people are who deal with production of software everyday but have little to no idea about the jobs of others outside of their realm. Comical stuff.

Would you mind explaining more of your reasoning? I don't think I fully understand why you're saying what you're saying.

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

#529

Post by kasane_teto »

echelon wrote: post #512
kasane_teto wrote: post #498

Earlier quoted context omitted.

ofc this shit happens when its my turn to be an adult. what’s like even the point anymore?

Fight for rigorous antitrust enforcement. Adopt open source models and platforms. We have a chance, but it's threading the needle and I'm not sure we'll make it.

I guess you’re right.

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

#530

Post by catoc »

adastra22 wrote: post #516
catoc wrote: post #470

Earlier quoted context omitted.

Thanks - would you have a source for this confirmation?

It’s how the LLM works. Anything accessed by the agent in the folder becomes input to the model. That’s what it means for the agent to access something. Those inputs are already “Input” in the ToS sense.

That an LLM needs input tokens to produce output was understood. That is not what the privacy policy is about. To me the policy reads Anthropic also subsequently persists (“collects”) your data. That is the point I was hoping to get clarified.
Post reply on HN