News for hackers. Stuff that matters.
Re:Ask HN: Would you trust an AI that sees and hears everyth... by aurintex on Saturday November 01, 2025 @06:43PM (#45786119)
Yeah, that's a great idea, I will add this to the feature list ;)

But I think for the V1, I'll stick to positive reinforcement. Not 100% sure "aversive conditioning" builds the long-term trust we're aiming for. ;)

Cheers!

Re:Ask HN: Would you trust an AI that sees and hears everyth... by conartist6 on Sunday November 02, 2025 @06:50AM (#45789631)
You're amazing! That's a really good idea!