Search results

Create the page "Recursive self-improvement" on this wiki! See also the search results found.

• My understanding of how IDA works
  ...umans are only "running the show" to the extent that they seeded the whole recursive process). In other words, it seems like Sovereigns would also be described
  9 KB (1,597 words) - 00:27, 6 October 2020
• Counterfactual of dropping a seed AI into a world without other capable AI
  ...were dropped into a world empty of other AI, it would undergo recursive self-improvement." [https://lw2.issarice.com/posts/5WECpYABCT62TJrhY/will-ai-undergo-discont
  3 KB (426 words) - 20:51, 15 March 2021
• List of technical AI alignment agendas
  * [[Recursive reward modeling]]
  586 bytes (56 words) - 21:29, 2 April 2021
• List of disagreements in AI safety
  ....com/p/KANSI/?l=1fy#subpage-1gp] "If you imagine steady improvement in the self-improvement, that doesn't give a local team a strong advantage." [https://docs.google.c * speed of improvement/discontinuities/recursive self-improvement once the AI reaches some critical threshold (like human baseline)
  21 KB (3,254 words) - 11:00, 26 February 2022
• Desiderata for dissolving the question
  ...ppen so often when thinking about cognitive reductions and not, say, about recursive programs? More generally, we seem to think about ourselves as Cartesian-by-
  6 KB (973 words) - 21:06, 30 July 2021
• Competence gap
  ...re AI algorithms are creating other AI algorithms (this includes recursive self-improvement, but is also more general/relaxed), to what extent will the AI be helping w
  3 KB (477 words) - 00:01, 30 May 2020
• RSI
  #redirect [[Recursive self-improvement]]
  40 bytes (3 words) - 22:50, 19 July 2020
• List of arguments against working on AI safety
  ...growth argument against AI safety]]: explosive growth (such as [[recursive self-improvement]] or [[em economy]]) are not possible, so there is no need to worry about t
  8 KB (1,245 words) - 00:29, 24 July 2022
• HCH
  '''HCH''' (a recursive acronym for '''humans consulting HCH''') is a theoretical scheme for [[ampl
  416 bytes (61 words) - 23:03, 25 February 2021
• Late 2021 MIRI conversations
  ...ves Eliezer's error is about the abstraction on consequentialism/recursive self-improvement being messier to apply to the real world than Eliezer expected); (3) the co
  6 KB (948 words) - 21:27, 1 August 2022