alt Hacker NewsCowork: Claude Code for the rest of your work
Comments
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: that's wonderful, but Claude Cowork does not use it.
For those of us who have built real systems at low levels I think the alarm bells go off seeing a tool like this - particularly one targeted at non-technical users
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.)
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.
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?
A CLI chat interface seems ideal for when you keep code "at a distance", i.e. if you hardly/infrequently/never want to peek at your code.
But for writing prose, I don't think chat-to-prose is ideal, i.e. most people would not want the keep prose "at a distance".
I bet most people want to be immersed in an editor where they are seeing how the text is evolving. Something like Zed's inline assistant, which I found myself using quite a lot when working on documents.
I was hoping that Cowork might have some elements of an immersive editor, but it's essentially transplanting the CLI chat experience to an ostensibly "less scary" interface, i.e., keeping the philosophy of artifacts separate from your chat.
>By default, the main thing to know is that Claude can take potentially destructive actions (such as deleting local files) if it’s instructed to.
What do the words "if it's instructed to" mean here? It seems like Claude can in fact delete files whenever it wants regardless of instruction.
For example, in the video demonstration, they ask "Please help me organize my desktop", and Claude decides to delete files.
Anthropic: we will do the Code button first, then we implement Non-Code button.
OpenAI: we will do the Non-Code button first, then we implement the Code button.
It's really quite amazing that people would actually hook an AI company up to data that actually matters. I mean, we all know that they're only doing this to build a training data set to put your business out of business and capture all the value for themselves, right?
I've been using Claude Code in my terminal like a feral animal for months. Building weird stuff. Breaking things. Figuring it out as I go.
Cowork is the nice version. The "here's a safe folder for Claude to play in" version. Which is great! Genuinely. More people should try this.
But!!! The terminal lets you do more. It always will. That's just how it works.
And when Cowork catches up, you'll want to go further. The gap doesn't close. It just moves.
All of this, though, is good? I think??
This looks useful for people not using Claude Code, but I do think that the desktop example in the video could be a bit misleading (particularly for non-developers) - Claude is definitely not taking screenshots of that desktop & organizing, it's using normal file management cli tools. The reason seems a bit obvious - it's much easier to read file names, types, etc. via an "ls" than try to infer via an image.
But it also gets to one of Claude's (Opus 4.5) current weaknesses - image understanding. Claude really isn't able to understand details of images in the same way that people currently can - this is also explained well with an analysis of Claude Plays Pokemon https://www.lesswrong.com/posts/u6Lacc7wx4yYkBQ3r/insights-i.... I think over the next few years we'll probably see all major LLM companies work on resolving these weaknesses & then LLMs using UIs will work significantly better (and eventually get to proper video stream understanding as well - not 'take a screenshot every 500ms' and call that video understanding).
I cannot see this page, I'm redirected to https://claude.com/fr-fr/blog/cowork-research-preview which don't exist. Private tab doesn't help
For those worried about irrevocable changes, sometimes a good plan is all the output.
Claude Code is very good at `doc = f(doc, incremental_input)` where doc is a code file. It's no different if doc is a _prompt file_ designed to encapsulate best practices.
Hand it a set of unstructured SOP documents, give it access to an MCP for your email, and have it gradually grow a set of skills that you can then bring together as a knowledge base auto-responder instruction-set.
Then, unlike many opaque "knowledge-base AI" products, you can inspect exactly how over-fitted those instructions are, and ask it to iterate.
What I haven't tried is whether Cowork will auto-compact as it goes through that data set, and/or take max-context-sized chunks and give them to a sub-agent who clears its memory between each chunk. Assuming it does, it could be immensely powerful for many use cases.
Every startup is at the mercy of the big 3 (OpenAI, Anthropic, Google).
They can and most likely will release something that vaporises the thin moat you have built around their product.
This feels like the first time in tech where there are more startups/products being subsumed (agar.io style) than being created.
It's a little funny how the "Stay in control" section is mostly about how quickly you can lose control (deleting files, prompt injections). I can foresee non-technical users giving access to unfortunate folders and getting into a lot of trouble.
Agents for other people, this makes a ton of sense. Probably 30% of the time I use claude code in the terminal it's not actually to write any code.
For instance I use claude code to classify my expenses (given a bank statement CSV) for VAT reporting, and fill in the spreadsheet that my accountant sends me. Or for noting down line items for invoices and then generating those invoices at the end of the month. Or even booking a tennis court at a good time given which ones are available (some of the local ones are north/south facing which is a killer in the evening). All these tasks could be done at least as well outside the terminal, but the actual capability exists - and can only exist - on my computer alone.
I hope this will interact well with CLAUDE.md and .claude/skills and so forth. I have those files and skills scattered all over my filesystem, so I only have to write the background information for things once. I especially like having claude create CLIs and skills to use those CLIs. Now I only need to know what can be done, rather than how to do it - the “how” is now “ask Claude”.
It would be nice to see Cowork support them! (Edit: I see that the article mentions you can use your existing 'connectors' - MCP servers I believe - and that it comes with some skills. I haven't got access yet so I can't say if it can also use my existing skills on my filesystem…)
(Follow-up edit: it seems that while you can mount your whole filesystem and so forth in order to use your local skills, it uses a sandboxed shell, so your local commands (for example, tennis-club-cli) aren't available. It seems like the same environment that runs Claude Code on the Web. This limits the use for the moment, in my opinion. Though it certainly makes it a lot safer...)
It’s kind of funny that apparently most of work that’s left after you automated software development is summarizing meetings and building slide decks.
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.
This sounds really interesting. Perhaps this is the promise that Copilot was not. I'm really hoping that this gives people like my wife access to all the things I use Claude Code for.
I use Claude Code for everything. I have a short script in ~/bin/ called ,cc that I launch that starts it in an appropriate folder with permissions and contexts set up:
~ tree ~/claude-workspaces -d
/Users/george/claude-workspaces
├── context-creator
├── imessage
│ └── tmp
│ └── contacts-lookup
├── modeler
├── research
├── video
└── wiki
Likewise, the `modeler` knows to create OpenSCAD files and so on, the `wiki` context knows that I use Mediawiki for my blog and have a Template:HackerNews and how to use it and so on. I find these make doing things a lot easier and, consequently, more fun.
All of this data is trusted information: i.e. it's from me so I know I'm not trying to screw myself. My wife is less familiar with the command-line so she doesn't use Claude Code as much as me, and prefers to use ChatGPT the web-app for which we've built a couple of custom GPTs so we can do things together.
Claude is such a good model that I really want to give my wife access to it for the stuff she does (she models in Blender). The day that these models get really good at using applications on our behalf will be wonderful! Here's an example model we made the other day for the game Power Grid: https://wiki.roshangeorge.dev/w/Blog/2026-01-11/Modeling_Wit...
The thing about Claude code, is that it's usually used in version controlled directories. If Claude f**s up badly, I can revert to a previous git commit. If it runs amock on my office documents, I'm going to have a harder time recovering those.
Nothing important is in my file system, its all in google drive, gmail, and slack.
Is anybody out there actually being more productive in their office work by using AI like this? AI for writing code has been amazing but this office stuff is a really hard sell for me. General office/personal productivity seems to be the #1 use-case the industry is trying to sell but I just don't see it. What am I missing here?
A week ago I pitched to my managers that this form of general purpose claude code will come out soon. They were rather skeptical saying that claude code is just for developers. Now they can see.
This looks pretty cool. I keep seeing people (an am myself) using claude code for more an more _non-dev_ work. Managing different aspects of life, work, etc. Anthropic has built the best harness right now. Building out the UI makes sense to get genpop adoption
Damn, yall can't do anything by yourselves.
can it play games for me? the factory must grow but I also need to cook dinner.
This is a great idea! I'm building something very similar with https://practicalkit.com , which is the same concept done differently.
It will be interesting for me, trying to figure out how to differentiate from Claude Cowork in a meaningful way, but theres a lot of room here for competition, and no one application is likely to be "the best" at this. Having said that, I am sure Claude will be the category leader for quite a while, with first mover advantage.
I'm currently rolling out my alpha, and am looking for investment & partners.
This is cool, but Claude for Chrome seems broken - authentication doesn't work and there's a slew of recent reviews on the Chrome extension mentioning it.
Sharing here in case anybody from Anthropic sees and can help get this working again.
It may seem off-topic, but I think it hurts developer trust to launch new apps while old ones are busted.
Under the hood, is this running shell commands (or Apple events) or is it actually clicking around in the UI?
If the latter, I'm a bit skeptical, as I haven't had great success with Claude's visual recognition. It regularly tells me there's nothing wrong with completely broken screenshots.
This seems like a thin client UX running Claude Code for the less technical user.
I’ve tried just about every system for keeping my desktop tidy: folders, naming schemes, “I’ll clean it on Fridays,” you name it. They all fail for the same reason: the desktop is where creative work wants to spill out. It’s fast, visual, and forgiving. Cleaning it is slow, boring, and feels like admin.
Claude Cleaner, I mean Cowork will be sweeping my desktop every Friday.
Im sure itll be useful for more stuff but man…
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.
I tried to get Claude to build me a spreadsheet last night. I was explicit in that I wanted an excel file.
It’s made one in the past for me with some errors, but a framework I could work with.
It created an “interactive artifact” that wouldn’t work in the browser or their apps. Gaslit me for 3 revisions of me asking why it wasn’t working.
Created a text file that it wanted me to save as a .csv to import into excel that failed hilariously.
When I asked it to convert the csv to an excel file it apologized and told me it was ready. No file to download.
I asked where the file was and it apologized again and told me it couldn’t actually do spreadsheets and at that point I was out of paid credits for 4 more hours.
I've been working with a claude-specific directory in Claude Code for non-coding work (and the odd bit of coding/documentation stuff) since the first week of Claude Code, or even earlier - I think when filesystem MCP dropped.
It's a very powerful way to work on all kinds of things. V. interested to try co-work when it drops to Plus subscribers.
This is the sort of stuff Apple should’ve been trying to figure out instead of messing with app corners and springboards.
We’re building something very similar but with files in the cloud instead.
Try it https://tabtabtab.ai
Would love some feedback!
This is the natural evolution of coding agents. They're the most likely to become general purpose agents that everyone uses for daily work because they have the most mature and comprehensive capability around tool use, especially on the filesystem, but also in opening browsers, searching the web, running programs (via command line for now), etc. They become your OS, colleague, and likely your "friend" too
I just helped a non-technical friend install one of these coding agents, because its the best way to use an AI model today that can do more than give him answers to questions. I'm not surprised to see this announced and I would expect the same to happen with all the code agents becoming generalized like this
The biggest challenge towards adoption is security and data loss. Prompt injection and social engineering are essentially the same thing, so I think prompt injection will have to be solved the same way. Data loss is easier to solve with a sandbox and backups. Regardless, I think for many the value of using general purpose agents will outweigh the security concerns for now, until those catch up
I see the sales people completed their takeover...
I'm a bit shocked to see so many negative comments here on HN. Yes, there are security risks and all but honestly this is the future. It's a great amplifier for hackers and people who want to get stuff done.
It took some training but I'm now starting almost all tasks with claude code: need to fill out some word document, organize my mail inbox, write code, migrate blog posts from one system to another, clean up my computer...
It's not perfect perfect, but I'm having fun and I know I'm getting a lot of things done that I would not have dared to try previously.
Isn't this just a UI over Claude Code? For most people, using the terminal means you could switch to many different coding CLIs and not be locked into just Claude.
YMMV but TFA page content body didn’t render for me until I disabled my local pihole.
Is there anything similar to this in the local world? I’m setting up a full local “ai” stack on a 48gb MacBook for my sensitive data ops. Using webui. Will still use sota cloud services for coding.
This is interesting because in the other thread about Anthropic/Claude Code, people are arguing that Anthropic is right to focus on what CC is good at (writing code).
I would like to thank the 100,000 people in Madagascar[1] who made it all possible by creating training data for ~€0.30 per hour.
Really like the look of this. I use Claude Code (and other CLI LLM tools) to interact with my large collection of local text files which I usually use Obsidian to write/update. It has been awesome at organization, summarization, and other tasks that were previously really time consuming.
Bringing that type of functionality to a wider audience and out of the CLI could be really cool!
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-cowork... tells users "Avoid granting access to local files with sensitive information, like financial documents" and "Monitor Claude for suspicious actions that may indicate prompt injection".
(I don't think it's fair to ask non-technical users to look out for "suspicious actions that may indicate prompt injection" personally!)