Comment

Comment on I Went All-In on AI. The MIT Study Is Right.

There’s no point telling it not to do x because as soon as you mention it x it goes into its context window.

It has no filter, it’s like if you had no choice in your actions, and just had to do every thought that came into your head, if you were told not to do a thing you would immediately start thinking about doing it.

source

Sort:hotnew top

kahnclusions@lemmy.ca ⁨1⁩ ⁨week⁩ ago
I’ve noticed this too, it’s hilarious(ly bad).

Especially with image generation. “Draw a picture of an elf.” Generates images of elves that all have one weird earring. “Draw a picture of an elf without an earing.” Great now the elves have even more earrings.

source
- MangoCats@feddit.it ⁨1⁩ ⁨week⁩ ago
  I find this kind of performance to vary from one model to the next. I definitely have experienced the bad image getting worse phenomenon - especially with MS Copilot - but different models will perform differently.
  
  source
MangoCats@feddit.it ⁨1⁩ ⁨week⁩ ago

There’s no point telling it not to do x because as soon as you mention it x it goes into its context window.

Reminds me of the Sonny Bono high speed downhill skiing problem: don’t fixate on that tree, if you fixate on that tree you’re going to hit the tree, fixate on the open space to the side of the tree.

LLMs do “understand” words like not, and don’t, but they also seem to work better with positive examples than negative ones.

source