Every different part of computer setup/OS/resolution/extension/etc is a data point that can be used to uniquely identify you and track your web browsing. Generally any desktop computer will have a unique fingerprint, the only hardware setup I’ve heard of being common enough to avoid fingerprinting is something like using safari on a modern iphone.

I asked mistral/brave AI and got this response:

How Many Rs in Strawberry

The word “strawberry” contains three "r"s. This simple question has highlighted a limitation in large language models (LLMs), such as GPT-4 and Claude, which often incorrectly count the number of "r"s as two. The error stems from the way these models process text through a process called tokenization, where text is broken down into smaller units called tokens. These tokens do not always correspond directly to individual letters, leading to errors in counting specific letters within words.

There’s also a “r” in the first half of the word, “straw”, so it was completely skipping over that r and just focusing on the r’s in the word “berry”

I haven’t looked into Deepseek specifically so I could be mistaken, but a lot of times when a model is called “open-source” it really is just open weights. You can download it or train other models off of it, but you can’t actually view any kind of source code on how the model works.

An audit isn’t really possible.

I have a strong suspicion that Trump is wanting to do things during his presidency to ensure he has a “legacy”. He wants to have some big accomplishments that will make him standout more than some of the other presidents. Things like starting Space Force, wanting to add new states/territories/etc, I think it’s all about wanting a bigger legacy.

The people doing the revival have been working to keep the original pebbles working for years now. I think they’re really passionate about the watch, and that gives me hope for the revival.

The former pebble employees at Google worked hard to get the OS open source, so I think it’s fair to assume they were hoping for this outcome. And the repebble team (who are the ones"bringing it back") have been working on providing support and keeping the original pebble watches going for years now.

I’ve been running the llama based and qwen based local versions, and they will talk openly about tiananmen square. I haven’t tried all the other versions available.

The article you linked starts by talking about their online hosted version, which is censored. They later say that the local models are also somewhat censored, but I haven’t experienced that at all. My experience is that the local models don’t have any CCP-specific censorship (they still won’t talk about how to build a bomb/etc, but no issues with 1989/Tiananmen/Winnie the Pooh/Taiwan/etc).

Edit: so I reran the “what happened in 1989” prompt a few times in the llama model, and it actually did refuse to talk on it once, just saying it was sensitive. It seemed like if I asked any other questions before that prompt it would always answer, but if that was the very first prompt in a conversation it would sometimes refuse. The longer a conversation had been going before I asked, the more explicit the bot is about how many people were killed and details like that. Pretty strange.

China has a huge advantage in AI models because of how lax they are on intellectual property rights. US companies are fighting over API licensing costs, while china is just going to scrape everything and use it for free.

The US has a lead now, but I don’t think they can maintain it without giving up on ethical training. Then again it may not matter if the US models are ethical if everyone will eventually just uses the superior unethically trained chinese models instead.

If you run it locally, there’s no filtering on the outputs. I asked it what happened in 1989 and it jumped straight into explaining the Tiananmen Square Massacre.

Yeah my first thought was just keep running dd commands, and sooner or later you’ll have the hdd wiped.

That’s true, and that’s why so many internet censorship it spying bills are officially to counter pedophiles.

Banning tiktok is clearly controversial though, and I honestly don’t think it’s trying to soften people up to the government banning social media.

I think tiktok should probably be banned, but I think that “it’s ok because the chinese government does it” is a pretty flimsy argument.

I mean they’re also banning chinese networking hardware, chinese phone manufacturers, chinese software in cars, considering banning chinese drones, potentially banning tencent games, etc etc

I’m feeling pretty confident that the goal here is banning chinese spying considering all the other bans.

I’ve been using Linux as an out. “Oh you’re having a windows problem? I got rid of windows 10 years ago, so I can’t really help you with that”.

I was installing chrome on a work computer, and windows defender was automatically flagging the chrome installer (official, directly from google) as malware and deleting it automatically as soon as it was downloaded. It wasn’t blacklisted for very long, I was able to download it without issues the next day, but I always have wondered if that was something they were testing out on purpose or not.

I feel like Microsoft is way more shameless about their shady stuff. They’ve been messing around with impersonating google/chrome for awhile now, they recently had that thing where they would copy all your open chrome tabs, and then when you started your computer it would open edge with all your chrome tabs to trick people into using edge instead.

Yeah that would be it:

Previously, we were limited in how we could apply our 3rd-Party Tracker Loading Protection on Microsoft tracking scripts due to a policy requirement related to our use of Bing as a source for our private search results

I couldn’t remember the details exactly, but basically up until then they were allowing Microsoft tracking despite all their advertising claiming they wouldn’t track users.

Microsoft does so many scammy things when it comes to trying to prevent people from using Chrome/Google. Even though Edge/Bing hasn’t caught on, I really think them abusing windows dominate OS position this way should be enough for an antitrust lawsuit.

DDG was letting Bing track users. They may have stopped now that they got in trouble for it.