Join the OpenRT discord server. The link can be found on their gitbook website. I believe they have some channels for Linux on the Surface 2

Edit: nvm, not sure about the surface 8, but maybe ppl there can still help

LLMs have no more beliefs than a parrot does. They just repeat whatever opinions/biases exist in their training data. Although, that’s not too different from humans in some respects.

Check out PostmarketOS for older machines/phones too. I got it working on an old Microsoft surface RT that would have been e-waste otherwise

Neat, but one needs to also trust that google isn’t an adversary

Extraordinary claims require extraordinary evidence.

So if I have two machines running the same local LLM and I pass a prompt between them, I’ve achieved data compression by transmitting the prompt rather than the LLM’s expected response to the prompt? That’s what I’m understanding from the article.

Neat idea, but what if you want to transmit some information that an LLM can’t tokenize and generate accurately?

Wow, so brave

As a German company, they should know a thing or two about appeasing facists

You guys actually allow websites to send you notifications? Pretty much every site that has asked me to allow notifications is one that I wouldn’t want notifications from.

I’ll tell my AI agent to go into the registry and disable itself.

This happened less than a year ago. Doubt regulators have done much since then https://apnews.com/article/chatbot-ai-lawsuit-suicide-teen-artificial-intelligence-9d48adc572100822fdbc3c90d1456bd0

Seems like the flat-earthers or sovereign citizens of this century

Tools for Humanity Surveillance

Its not the design. Its the ads, bots, and lack of privacy. I quit it more than a year ago

Of the companies that might buy Chrome, I hope DuckDuckGo gets it.

A product that has a warranty which depends on any “predictive” metric is probably a scam, tbh.

Paying protection money not to get broken up for being monopolies. No amount of money will protect them from the whims of a mad king.

Bootlickers. At least this makes it easy to know what companies not to support

At some point, the vetting process will end up being more time consuming than actively moderating the instance, it will still not be 100% effective.

They work well when being correct doesn’t matter