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

581–590 of 593 posts

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

#581

Post by catoc »

adastra22 wrote: post #579
catoc wrote: post #578

Earlier quoted context omitted.

So when using Cowork on a local folder and asking it to " create a new spreadsheet with a list of expenses from a pile of screenshots ", those screenshots may[*] become part of the " collected Inputs " kept by Anthropic. [*]"may" because depending on the execution, instead of directly uploading the screenshots, a (python) script may be created that does local processing and only upload derived output

Yes, in general. I think in your specific example it is more likely to ingest the screenshots (upload to Anthropic) and use its built-in vision model to extract the relevant information. But if you had like a million screenshots, it might choose to run some Python OCR software locally instead. In either case though, all the tool calls and output are part of the session and therefore Input. Even if it called a local O…

When local compute is more efficient data may remain local (e.g. when asking it to "find duplicate images" in millions of images it will likely (hopefully) just compute hashes and compare those), but complete folder contents are just as likely to be ingested (uploaded) and considered "Inputs", for which even the current Privacy Policy already explicitly says these will be "collected" (even when opting-out of allowing subsequent use for training).

To be clear: I like what Anthropic is doing, they appear more trustworthy/serious than OpenAI, but Cowork will result in millions of unsuspecting users having complete folders full of data uploaded and persisted on servers, currently, owned by Anthropic.

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

#582

Post by vita7777777 »

runarberg wrote: post #480
jamwil wrote: post #474

Earlier quoted context omitted.

That’s not really reasonable to assume at all. Five minutes of research would give you a pretty strong indication of his character. The dude does not need to self-aggrandize; his reputation precedes.

Perhaps. But perhaps this era of AI slop leaves a foul taste in many people’s mouth. I don‘t know the reputation, all I see is somebody who felt the need to AI generate a picture and post it on HN. This is slop, and I personally get bad vibes from people who post AI generated slop, which leaves me with all sorts of assumptions about their character. To clarify, they are here to have fun, they liked the joke about cow…

This really is unnecessarily harsh. As someone who's been reading Simon's blog for years and getting a lot of value from his insights and open source work, I'm sad to see such a snap dismissive judgement.

"all sorts of assumptions about [someone's] character" based on one post might not be a smart strategy in life.

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

#583

Post by brazukadev »

vita7777777 wrote: post #582
runarberg wrote: post #480

Earlier quoted context omitted.

Perhaps. But perhaps this era of AI slop leaves a foul taste in many people’s mouth. I don‘t know the reputation, all I see is somebody who felt the need to AI generate a picture and post it on HN. This is slop, and I personally get bad vibes from people who post AI generated slop, which leaves me with all sorts of assumptions about their character. To clarify, they are here to have fun, they liked the joke about cow…

This really is unnecessarily harsh. As someone who's been reading Simon's blog for years and getting a lot of value from his insights and open source work, I'm sad to see such a snap dismissive judgement. "all sorts of assumptions about [someone's] character" based on one post might not be a smart strategy in life.

I'd say is necessarily harsh. It is not as if Simon's opinions on AI were really better than others here that are as technical as his.

He is prolific, and being at the top of every HN thread is what makes him look like a reference but there are other 50+ people talking interesting things about AI that are not getting the deserved attention because every top AI thread we are discussing a pelican riding a bike.

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

#584

Post by mkbkn »

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.)

Can you release custom GPTs like ChatGPT has?

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

#585

Post by fennecfoxy »

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-…

Problem is technical people on average (I wouldn't say all of us) know what we don't know. I'm naturally cautious when running new stuff or even just trying something new in life.

This is why the Android permissions system of "allow this app to x, y, z" whilst great for me, isn't really a good system for the average person, because what do they do "yes, yes, yes, just let me see my Tiktoks!1111"

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

#586

Post by fennecfoxy »

Hmm. I'm building something (quick and dirty) at the moment that looks at analysing customer service data.

Something like this is promising but from what I can see, still lacking. So far I've been dealing with the regular issues (models aren't actually that smart, work with their strengths and weaknesses) but also more of the data problem - simple embeddings just aren't enough, imo. And throwing all of the data at the model is just asking for context poisoning, hallucinations and incorrect conclusions.

Been playing with instruction tuned embeddings/sentiment and almost building a sort of "multimodal" system of embedding to use with RAG/db calls. What I call "Data hiding" as well - allowing the model to see the shape of the data but not the data itself, except only when directly relevant.

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

#587

Post by nomagicbullet »

PessimalDecimal wrote: post #502
itake wrote: post #419

Earlier quoted context omitted.

"Move fast and break things" I could spend an extra 5 minutes doing it "right" or I can get what I need done and have a 0.001% chance of there ever being a problem (since there are other security measure in place, like firewalls, api key rotation, etc.) Even when security gaps are exploited, the fallout tends to be minimal. Companies that had their entire database of very sensitive information leaked are still growin…

How many times do you have to roll the dice with .001% of disaster before it strikes? How often are you using the tool in this way?

About 100,000 rolls on average.

About 2.7 rolls per day for 100 years

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

#588

Post by catoc »

simonw wrote: post #35
redfloatplane wrote: post #30

Earlier quoted context omitted.

I do get a "Setting up Claude's workspace" when opening it for the first time - it appears that this does do some kind of sandboxing (shared directories are mounted in).

It looks like they have a sandbox around file access - which is great! - but the problem remains that if you grant access to a file and then get hit by malicious instructions from somewhere those instructions may still be able to steal that file.

I just tried Cowork.... It crashed with "Claude Code process terminated by signal SIGKILL".

Is Cowork Claude-Code-but-with-sandbox ?

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

#589

Post by TeMPOraL »

eli wrote: post #574
TeMPOraL wrote: post #331

Earlier quoted context omitted.

> But you could totally have a tool that lets you use Claude to interrogate and organize local documents but inside a firewalled sandbox that is only able to connect to the official API. Any such document or folder structure, if its name or contents were under control of a third party, could still inject external instructions into sandboxed Claude - for example, to force renaming/reordering files in a way that will p…

I'm not following the threat model that begins with a malicious third party having control over my files

Unless you've authored every single file in question yourself, their content is, by definition, controlled by a third party, if with some temporal separation. I argue this is the typical case - in any given situation, almost all interesting files for almost any user came from someone else.

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

#590

Post by carlosbaraza »

hoss1474489 wrote: post #563
carlosbaraza wrote: post #486

Earlier quoted context omitted.

Same thing for me. It crashes. Submitted a report with the "Send to Apple" report, not sure if there is any way the team can retrieve these reports.

Restarting the machine got Cowork working for me.

some things will never change :)
Post reply on HN