osten

• ostenJul 13, 2023, 11:10 AM

  4 points

  0

  on: Elon Musk an­nounces xAI

  So will the maximally curious AI be curious about what would happen if you genetically modified all humans to become unicorns?

• ostenApr 9, 2023, 5:54 AM

  22 points

  5

  on: Agen­tized LLMs will change the al­ign­ment landscape

  But it also provides incredibly easy interpretability, because these systems think in English.

  I’m not sure this point will stand because it might be cheaper to have them think in their own language: https://​​www.lesswrong.com/​​posts/​​bNCDexejSZpkuu3yz/​​you-can-use-gpt-4-to-create-prompt-injections-against-gpt-4

• ostenJan 17, 2023, 7:58 PM

  0 points

  0

  on: Five Rea­sons to Lie

  Mr ChatGPT, does my bum look too big in that dress?

• ostenDec 5, 2022, 5:44 PM

  1 point

  0

  on: Who are some promi­nent rea­son­able peo­ple who are con­fi­dent that AI won’t kill ev­ery­one?

  Jeff Hawkins may qualify, see his first Lex Fridman interview: 1:55:19.

• ostenAug 1, 2021, 4:57 PM

  1 point

  on: Cog­ni­tive Im­pacts of Co­caine Use

  Are you sure about the imcreased sustained attention among cocaine users? The abstract in your link seems to suggest the opposite.

• ostenJun 6, 2021, 9:48 PM

  6 points

  on: So­cial be­hav­ior curves, equil­ibria, and radicalism

  Enjoyable. I’m surprised Asch’s conformity experiments are not mentioned, e.g. https://​​www.lesswrong.com/​​posts/​​WHK94zXkQm7qm7wXk/​​asch-s-conformity-experiment.