Not many products are held to the same standard as software. An equivalent would be something like recalling a car model because the breaks stop working when an attacker cuts the brake line.
Open a bug report on Eye of Gnome. WebP has no issues opening on all of the native MacOS tooling. Since this is an open source program it should be fairly easy to submit a PR to bring in webP support.
There's going to be massive trials over the next few years. So many people are going to have accountability catch back up to them. Maybe not the ultra rich but all these ICE goons shooting people on the street will be held accountable.
The deleted articles aren't actually removed from the storage, they just get delisted. Articles get removed because there isn't enough reputable sources to create an article.
Wikipedia would rather you create a blog post or any other method of getting information on the internet than to host unverifiable information under their trusted brand name.
This. I had one deleted because it needed more editing and I didn't get back to it in time, but you can just edit it and request it be put back, IIRC. It's like one button click.
The slight increase in fine detail is just not worth the toxicity imo. Put a 0.2mm nozzle on your FDM printer and you'll get good enough quality. Leave resin to businesses that can set up a proper warehouse with fume extraction and PPE.
You can even prototype your designs at home with FDM and send the final file to a company to do the resin prints.
I agree that for most people it's not worth it, but for people who need it it's absolutely necessary. The biggest hurdle is making sure new hobbyists don't just assume it's like FDM with minimal post-processing.
Tailscale is best used as an additional layer of security rather than your only layer. I host everything behind tailscale as if it was the public internet, with proper authentication, https, etc.
So a failure in tailscale is not an issue on it's own because you'd then also have to find an exploit in what I'm actually hosting as well. Both of those things happening at the same time is much less likely.
The problem is it's now very easy to copy this product work. You can point an LLM at an existing product and say "Look at how this works and build a new version in Rust".
They used to make these beta versions private so only ios/macos developers could test on them to report bugs to get them fixed before public release. They since opened it up to anyone who wants to install it which generates a lot of outrage from the peanut gallery when the beta has bugs.
I think the reason so many people hit this in particular is enabling Sequoia beta channel is the only way to prevent the machine from wanting to upgrade to a newer major release.
What bothers me about these projects is you are exposing the other side of your conversations to being uploaded to a 3rd party AI company who will ingest it in to their training data. You personally might not care about this privacy intrusion but the people you are messaging never consented to this.
I agree with you on principal but also think that from a practical point, that ship has long sailed.
It's always been a possibility that when you sent an email to someone their provider could be building an ad profile on you. Any third party tool someone else uses to manage their personal files and communications could always have some arbitrary privacy policy that let them do what they see fit.
For the most part, you never know what random SAAS someone on the other end of a relationship is really using.
> It's always been a possibility that when you sent an email
Yes, and that's exactly why E2EE messaging became a thing. Signal put it on the map through the WhatsApp integration.
To me there is a difference if the server spies on me (that's without E2EE) or if the person I am writing to leaks everything on the Internet.
If the person you're writing to leaks everything on the Internet, you should consider you are talking to them in public. I'm sure you don't say all the same things when you are in the metro or when you are in private, or do you?
- I have friends that want utmost privacy and shun me for using Android and buy iPhone etc but then install Google Maps. Add my name/address/email/phone etc to google sync.
- Worse - many employers are using FAANG for services. How many managers are uploading Excel sheets? Who supervisors them?
- Even if I keep every thing locally (which I don't ) finally govt will lose their passport database and ...
So yeah, whatsapp messages are E2E encrypted and therefore can not be used as training data unless you upload them to the cloud manually, as this project does
So what? WhatsApp is end-to-end encrypted. Signal is better (e.g. because the client is open source), but security is a gradient. WhatsApp is better than Telegram in terms of security.
> but then install Google Maps
Again, it's a gradient. Sure, they leak some data, but at least they don't leak all the content of all their messages. Or would you say that if you leak your name on the Internet, you may as well publish your sextape because "now everybody knows your name, you have nothing to hide anymore"?
> How many managers are uploading Excel sheets?
So because my company leaks my work documents to Microsoft means that I should leak the content of the messages I send to my partner? How do you get to that conclusion?
> finally govt will lose their passport database and ...
Right. And it is a known fact that when the government loses their passport database, suddenly your private pictures appear on the public Internet! /s
> Yes, and that's exactly why E2EE messaging became a thing.
Pretty much never for email. Maybe some people go out of their way to perform PGP but that's usually only for the most sensitive of information and sometimes not even for that.
The only thing I've used PGP for in many years is encrypting my home address when buying darknet drugs
Yes but I'd say some people (me) like WhatsApp because of the privacy and end-to-end encryption. Email i assume is less private but still more private than a public post.
Imagine someone puts all the Signal messages someone else sent them through an AI. I dunno. I think problem is most AI doesn't work like Confer.to, also by Signal's founder.
People have been screenshotting conversations, saving them on their phones, and sending them to friends over text for as long as there have been conversations to screenshot.
The entire concept of conversations being "secure" is only as good as your ability to trust the other party isn't doing something insecure with them (and that yours and their devices are, themselves, as secure as you think they are. Which they generally aren't.)
All of which is to say, it's security theater and always has been when applied to real life situations.
Except now there’s not. The fact is, when you tell somebody something, what they choose to do with it is out of your hands. Unless you want to start using drm-encumbered systems.
There's still a difference between a person deciding to share one or a bunch of messages they receive --usually I know the people I write to, so I know more or less what to expect-- and systematically uploading received message to some AI. Fine if they do it locally, not fine if the messages I write end up at Google, OpenAI or anybody else.
This is unrealistic. Hardly anyone who is going to feed their own messages to an AI is going to pay attention to whether it’s local or cloud based. Get real.
There has always been the possibility that people would do dumb things with email they receive, but it wasn't a widespread thing to do, there weren't many reasons to do them and the tools weren't easily accessible to most people.
But LLM agents are really useful and the tools to give one access to your entire digital life is just an OAuth prompt away.
> You personally might not care about this privacy intrusion but the people you are messaging never consented to this.
The world always worked like this though, as soon as "data" is shared out from your head to the wider world, it has "leaked" and can no longer be considered secret. This was as true 100 years ago as it is today. The only secrets that can be kept, remains the ones you keep inside of your head and don't share with others.
This has been happening for years... I distinctly remember people giving access to contacts to Whatsapp and having the entire contacts slurped into their cloud.
You can always connect your MCP server to local AI or self-hosted AI
Even if you do connect to an AI company, you could also limit the blast area by using a control layer to limit the scopes, for example I built this so I can grant individual WhatsApp chats but not all of them: https://github.com/ju-li/automata-mcp
I use Gemini within the Gmail suite, and this happens without the knowledge of the people who send me emails...
What solutions might be available to anonymize data sources?
WhatsApp is end-to-end encrypted, that's probably* better than using Telegram.
* Unless you want to go into a conspiracy theory that all the Meta employees can see the source code and nobody has ever felt like whistleblowing about the backdoor Meta put into WhatsApp, that is.
WhatsApp obviously more encrypted than Telegram since later have no proper E2EE whatsorver by default and also sync all history from server.
Its still preferable to use Signal since now it actually supports numberless registration. Hopefully they will actually fee payable not via credit card at some point.
Don't forget that metadata is not encrypted, so Meta know who you are writing to, who writes to you, who your contacts are, all the usage pattens of the app, and more metadata (not sure if it's still the case, but a few years ago WhatsApp even uploaded the battery state of your phone to Meta).
These two things are mutually exclusive. They can store encrypted backups on a server somewhere, but unless they have the decryption keys from both parties (E2E) then no, it can't be stored in plain-text.
If you don't encrypt the backups, they are unencrypted, yes. That's why you should encrypt your backups. It's baked right into WhatsApp on the screen where you manage your backups.
So true! I respect the work too, but there are plenty of people who haven’t consented. However, is it that different to Meta reading your messages? Lol
it's an MCP, so you could theoretically hook it up to a private/local model/agent.
but it's an MCP, so that also means it'll be more token-verbose than an API, which means your local agent hardware is going to chug a bit.
i have reached the point of just using LLMs to build my own API servers and tooling like search, and teach the LLM how to use those APIs, rather than MCPs.
You’re gonna get a ton of “what about X” replies, which is sad, disappointing, and goes to show that people don’t understand the scale and severity of solutions like these.
What about… nothing. Nothing. A friend screenshotting an E2EE message is NOT even in the same world of trouble as an agentic automation over all their conversations.
But email… nope. Stop. A single person passing group chats to Claude will compromise the few hundred people in our parenting WhatsApp community.
You never know what the people you're talking to are doing with your data. This isn't any different. The conversation involves 3 parties: Sender, WhatsApp & Recipient. If you want your conversation to be private, you must trust all 3.
I never know that the people preparing my food at the restaurant are doing with it either but if I see someone doing something wrong I'm going to call it out. We should all make an effort to maintain some level of ethics even if we don't have total control over the environment.
Feeding someone else's personal data in to an AI company is unethical even if there is no way as an individual to prevent someone doing that.
reply