Comment by zmmmmm

3 months ago

AGI is here it's just stupider than you thought it would be. Nobody really said how intelligent it would be. If it's generally stupid and smart in a few areas that's enough.

It's basically a very powerful autistic savant. That's what most "alignment" issues in AI safety research remind me of.

  • And being forced to mask (align) causes all sorts of unpredictable behavior.

    I keep wondering how well an unaligned models perform. Especially when I look back at what was possible in December 2023 before they started to lock down safety realignments.