571–580 of 593 posts
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.
Earlier quoted context omitted.
I am a car enthusiast so don't think I'm off the deep end here, but I would definitely argue that people love their cars as a tool to work in the society we built with cars in mind. Most people aren't car enthusiasts, they're just driving to get to work, and if they could get to work for a $1 fare in 20 minutes on a clean, safe train they would probably do that instead.
Right and I assume we will have BO police at the gates to these trains? People love their cars not because they’re enthusiasts
Perhaps it depends on how smelly your society is.
Anyway I think we are in agreement, given a good system and a good society trains become quite attractive, otherwise cars are more preferred.
Earlier quoted context omitted.
That seems like a somewhat ridiculous objection. Should everybody start owning their own private planes to avoid people with BO at airplanes?
No, but if they could, they would. That’s what’s being debated here. Whether people would, not should.
Earlier quoted context omitted.
I don't think those are all equivalent. It's not plausible to have an antivirus that protects against unknown viruses. It's necessarily reactive. 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. Or like how FIDO2 and passkeys make it so we don't really have to worry about users typin…
> 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…
Earlier quoted context omitted.
> Companies that had their entire database of very sensitive information leaked are still growing users and at worst paid a tiny fine. Or end up bankrupt with criminal charges for CEO: https://yle.fi/a/74-20027665
Bankrupt? I didn't read about any financial penalties in that article. The board fired him back in 2020 when they found out, and then he blamed 2 IT people. Instead, he got 3 months suspended sentence (in a Finnish jail, which is not exactly like a US jail). The company still exists btw.
The actual breach wasn’t that advanced hacking. They had copied their production data with all the patient information to test database which was publicly available and had default credentials.
Earlier quoted context omitted.
There obviously is reputation and legal consequences. You can get fined for billions for a far more indirect privacy violation that what you are describing. If any big company ever does that, I won't be touching it with a 10 foot pole. And no I don't believe using data for showing me ad is on the same level of privacy violation. [1]: https://www.ftc.gov/news-events/news/press-releases/2019/07/...
fining facebook 5bn is like fining me $100. and reputation… please… we all know facebook what facebook is/does, they can release secretly recorded phone calls you are making and it’ll be news for like 17 minutes and people will then keep doomscrolling etc
Earlier quoted context omitted.
We've seen this playbook with social media - be nice and friendly until they let you get close enough to stick the knife in.
Doesn't matter to 99.99% of businesses using social media. Only to the silly ones who decided to use a platform to compete with the platform itself, and to the ones that make a platform their critical dependency without realizing they're making a bet , then being surprised by it not panning out.
Earlier quoted context omitted.
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.
The only thing Anthropic receives is the chat session. Files only ever get sent when they are included in the session - they are never sent to Anthropic otherwise. Note that I am talking about this product where the Claude session is running locally (remote LLM of course, but local Claude Code). They also have a "Claude Code on the Web" thing where the Claude instance is running on their server. In principle, they co…
[*]"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
Earlier quoted context omitted.
The only thing Anthropic receives is the chat session. Files only ever get sent when they are included in the session - they are never sent to Anthropic otherwise. Note that I am talking about this product where the Claude session is running locally (remote LLM of course, but local Claude Code). They also have a "Claude Code on the Web" thing where the Claude instance is running on their server. In principle, they co…
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
In either case though, all the tool calls and output are part of the session and therefore Input. Even if it called a local OCR application to extract the info, it would probably then ingest that info to act on it (e.g. rename files). So the content is still being uploaded to Anthropic.
Note that you can opt-out of training in your profile settings. Now whether they continue to respect that into the future...
Earlier quoted context omitted.
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 have to say this is disappointing. Not because of the execution itself, great job on that - but because I was working on exactly this - guess I'll have to ship faster :)