The really sucky thing about using AI is that you can’t verify what is giving you responses. You cannot trust it. They can tell you the base model, but you have to believe them; and even if they could prove it, most #LLM providers are running orchestration layers on top of the #AI feeding it other data and allowing the AI to fetch its own (by proxy) external data. So there’s no telling where it builds its response from. The safest would be to self host. You cannot trust it verify the base models you have. And then you can run your own tooling/orchestration on the model. For now we don’t have better solution, so we just need to be cautious. But that seems like the only sane and safe future for me. Let’s make it happen

When everyone is shouting a one sided opinion about an ongoing crisis, it immediately makes me doubt it and think “psyop”

Excited to use @White Noise but waiting for Amber support.

I don't remember Spa being cancelled so often back in the day. It just feels like they've gotten softer. I guess it might be because they're faster and the aero makes more spray, but still it's so annoying - at such a great track. #f1 #formula1

Can’t for the life of me get my new little archlinux server to boot with drip dropbear in initramfs to allow me to ssh in and unlock the luks partition. Getting annoying.

Does anyone else have an eye-rolling/irritation response when you see “Web3” mentioned in an article as if it’s a thing?