sarahhw

What is re­cur­sive self-im­prove­ment, and what would it mean to ban it?

• sarahhw 14 Jan 2025 13:43 UTC

  3 points

  1 ∶ 0

  in reply to: Greg_Colbourn ⏸️ ’s comment on: Are AI safe­ty­ists cry­ing wolf?

  I think some number of crying-wolf-adjacent incidents in the future are inevitable as I said in the post. Doesn’t mean we can’t at least try to make it harder for people to weaponise them against us by hedging, acknowledging uncertainty etc.
  
  like I said, this is just my opinion. open to arguments for why signalling confidence is actually the right move, even at the risk of lost credibility

• sarahhw 14 Jan 2025 11:29 UTC

  3 points

  1 ∶ 0

  in reply to: Ryan Greenblatt’s comment on: Are AI safe­ty­ists cry­ing wolf?

  I have mixed feelings about the AIS memes account but would generally agree that they tend to sensationalise things. I guess I still wouldn’t describe this as “crying wolf” in the way I’ve defined it, but maybe my definition is too pedantic and misses the spirit of the complaint.

Are AI safe­ty­ists cry­ing wolf?

I read ev­ery ma­jor AI lab’s safety plan so you don’t have to