Search results

Create the page "Serious context of use" on this wiki! See also the search results found.

• Soft-hard takeoff
  the only places where i've found any discussion of anything similar to this: ...AI capabilities that are potentially decisive when employed by some group of ingenious, well-resourced human actors.
  8 KB (1,206 words) - 01:43, 2 March 2021
• Hardware argument for AI timelines
  In the context of [[AI timelines]], the '''hardware argument''' is a common argument structur ...mans, amount of computation required to raise a human to adulthood, amount of computation required to run an adult human brain, etc.
  5 KB (740 words) - 00:24, 12 July 2021
• List of disagreements in AI safety
  This is a '''list of disagreements in AI safety''' which collects the list of things people in AI safety seem to most frequently and deeply disagree abou Many of the items are from <ref>[https://drive.google.com/file/d/1wI21XP-lRa6mi5h0d
  21 KB (3,254 words) - 11:00, 26 February 2022
• People watching
  '''People watching''', according to me, refers to the art/science/act of observing people, judging them, classifying them, analyzing them, finding t ...r person Y has reset, instead of accumulating. you want to avoid this sort of thing happening. human memory sucks, etc.
  11 KB (1,847 words) - 00:52, 17 July 2021
• Linked list proof card
  ...f (or rather, more like a "cumulative" linked list where each card has all of the previous steps listed, not just the previous step). ...it sound like each card is a linked list, rather than that the collection of cards forms a linked list. Maybe "linked list proof method" or something is
  3 KB (620 words) - 01:06, 17 July 2021
• Iteration cadence for spaced repetition experiments
  ...nature of spaced repetition, any experiment that tries to test some aspect of it will take months to complete. This is because in order to see how much y ...things that makes academic work on spaced repetition not very useful. Most of them do very short-term reviews.
  3 KB (554 words) - 07:49, 19 May 2021
• Something like realism about rationality
  ...n one specific disagreement. This topic comes up when discussing the value of [[MIRI]]'s [[HRAD]] work. ...been discussed for a long time, under various names. (e.g. intelligibility of intelligence?)
  7 KB (1,110 words) - 20:24, 26 June 2020
• List of AI safety projects I could work on
  ...way that doesn't require "re-doing" the same step (because I lost whatever context I had when working on it initially), and a single evening can also make def ...), or because it requires keeping lots of things in my head so I cannot be context-switching with other tasks (i.e. if I work on it for a few hours, then I mi
  6 KB (927 words) - 14:25, 4 February 2022
• Medium that reveals flaws
  A '''medium that reveals flaws''' is a medium that reveals the flaws of the content produced in it. ...presented as an essay or news reporting, it is not so obvious which pieces of info are missing.
  3 KB (557 words) - 04:09, 16 July 2021