Strange | News & Top Stories on DeepNewz

If Artificial General Intelligence has an okay outcome, what will be the reason?

Mar 24, 2:01 PMJan 2, 7:59 AM

584365493

OptionProbability

J. Something 'just works' on the order of eg: train a predictive/imitative/generative AI on a human-generated dataset, and RLHF her to be unfailingly nice, generous to weaker entities, and determined to make the cosmos a lovely place.

B. Humanity puts forth a tremendous effort, and delays AI for long enough, and puts enough desperate work into alignment, that alignment gets solved first.

C. Solving prosaic alignment on the first critical try is not as difficult, nor as dangerous, nor taking as much extra time, as Yudkowsky predicts; whatever effort is put forth by the leading coalition works inside of their lead time.

G. It's impossible/improbable for something sufficiently smarter and more capable than modern humanity to be created, that it can just do whatever without needing humans to cooperate; nor does it successfully cheat/trick us.

Something wonderful happens that isn't well-described by any option listed. (The semantics of this option may change if other options are added.)

K. Somebody discovers a new AI paradigm that's powerful enough and matures fast enough to beat deep learning to the punch, and the new paradigm is much much more alignable than giant inscrutable matrices of floating-point numbers.

M. "We'll make the AI do our AI alignment homework" just works as a plan. (Eg the helping AI doesn't need to be smart enough to be deadly; the alignment proposals that most impress human judges are honest and truthful and successful.)

I. The tech path to AGI superintelligence is naturally slow enough and gradual enough, that world-destroyingly-critical alignment problems never appear faster than previous discoveries generalize to allow safe further experimentation.

O. Early applications of AI/AGI drastically increase human civilization's sanity and coordination ability; enabling humanity to solve alignment, or slow down further descent into AGI, etc. (Not in principle mutex with all other answers.)

You are fooled by at least one option on this list, which out of many tries, ends up sufficiently well-aimed at your personal ideals / prejudices / the parts you understand less well / your own personal indulgences in wishful thinking.

D. Early powerful AGIs realize that they wouldn't be able to align their own future selves/successors if their intelligence got raised further, and work honestly with humans on solving the problem in a way acceptable to both factions.

E. Whatever strange motivations end up inside an unalignable AGI, or the internal slice through that AGI which codes its successor, they max out at a universe full of cheerful qualia-bearing life and an okay outcome for existing humans.

F. Somebody pulls off a hat trick involving blah blah acausal blah blah simulations blah blah, or other amazingly clever idea, which leads an AGI to put the reachable galaxies to good use despite that AGI not being otherwise alignable.

H. Many competing AGIs form an equilibrium whereby no faction is allowed to get too powerful, and humanity is part of this equilibrium and survives and gets a big chunk of cosmic pie.

N. A crash project at augmenting human intelligence via neurotech, training mentats via neurofeedback, etc, produces people who can solve alignment before it's too late, despite Earth civ not slowing AI down much.

A. Humanity successfully coordinates worldwide to prevent the creation of powerful AGIs for long enough to develop human intelligence augmentation, uploading, or some other pathway into transcending humanity's window of fragility.

L. Earth's present civilization crashes before powerful AGI, and the next civilization that rises is wiser and better at ops. (Exception to 'okay' as defined originally, will be said to count as 'okay' even if many current humans die.)

If you write an argument that breaks down the 'okay outcomes' into lots of distinct categories, without breaking down internal conjuncts and so on, Reality is very impressed with how disjunctive this sounds and allocates more probability.

17

11

10

8

7

6

5

4

3

2

1

Who will appear in "Avengers: Secret Wars"?

Mar 25, 10:17 AMMay 7, 11:59 AM

563827

OptionProbability

Tom Holland (Peter Parker / Spider-Man)

Anthony Mackie (Sam Wilson / Captain America)

Pedro Pascal (Reed Richards / Mister Fantastic)

Benedict Cumberbatch (Dr. Stephen Strange)

Joseph Quinn (Johnny Storm / Human Torch)

Samuel L. Jackson (Nick Fury)

Robert Downey, Jr. (Victor von Doom / Doctor Doom, Tony Stark / Iron Man)

Vanessa Kirby (Sue Storm / Invisible Woman)

Ebon Moss-Bachrach (Ben Grimm / The Thing)

Paul Rudd (Scott Lang / Ant-Man)

Chris Hemsworth (Thor)

Charlie Cox (Matt Murdock / Daredevil)

Julia Louis-Dreyfus (Valentina Allegra de Fontaine)

Pom Klementieff (Mantis)

Sebastian Stan (Bucky Barnes / Winter Soldier / White Wolf)

Simu Liu (Shang-Chi)

Danny Ramirez (Joaquin Torres / Falcon)

Iman Vellani (Kamala Khan / Ms. Marvel)

Ryan Reynolds (Wade Wilson / Deadpool)

Mark Ruffalo (Bruce Banner / Hulk)

Dominique Thorne (Riri Williams / Ironheart)

Florence Pugh (Yelena Belova / Black Widow)

Benedict Wong (Wong)

Chris Pratt (Peter Quill / Star-Lord)

Vin Diesel (Groot)

Jeremy Renner (Clint Barton / Hawkeye)

Wyatt Russell (John Walker / U.S. Agent)

Brie Larson (Carol Danvers / Captain Marvel)

Hannah John-Kamen (Ava Starr / Ghost)

Letitia Wright (Shuri / Black Panther)

Karen Gillan (Nebula)

Tatiana Maslany (Jennifer Walters / She-Hulk)

David Harbour (Alexei Shostakov / Red Guardian)

Hailee Steinfeld (Kate Bishop / Hawkeye)

Teyonah Parris (Monica Rambeau)

Xochitl Gomez (America Chavez)

Kathryn Newton (Cassie Lang)

Bradley Cooper (Rocket Raccoon)

Will Poulter (Adam Warlock)

Tenoch Huerta Mejía (Namor)

Don Cheadle (James "Rhodey" Rhodes / War Machine)

Tessa Thompson (Valkyrie)

Winston Duke (M'Baku)

Elizabeth Olsen (Wanda Maximoff / Scarlet Witch)

Paul Bettany (Vision)

Kathryn Hahn (Agatha Harkness)

Danai Gurira (Okoye)

Oscar Isaac (Marc Spector / Moon Knight, Steven Grant / Mr. Knight, Jake Lockley)

Hayley Atwell (Peggy Carter / Captain Carter)

Tom Hiddleston (Loki)

Mahershala Ali (Blade)

Hugh Jackman (James "Logan" Howlett / Wolverine)

Sean Gunn (Kraglin)

Chris Evans (Steve Rogers / Captain America)

Alaqua Cox (Maya Lopez / Echo)

Lupita Nyong'o (Nakia)

Wil Deusner (Skaar)

Gemma Chan (Sersi)

Kumail Nanjiani (Kingo)

Lia McHugh (Sprite)

Brian Tyree Henry (Phastos)

Barry Keoghan (Druig)

Harry Styles (Eros / Starfox)

Patton Oswalt (Pip the Troll)

Kit Harington (Dane Whitman)

Yahya Abdul-Mateen II (Simon Williams / Wonder Man)

Ralph Ineson (Galactus)

Evangeline Lilly (Hope van Dyne / Wasp)

Seth Green (Howard the Duck)

Tobey Maguire (Peter Parker / Spider-Man)

Zoe Saldaña (Gamora)

Dave Bautista (Drax)

Angelina Jolie (Thena)

Gael García Bernal (Jack Russell / Werewolf by Night)

Scarlett Johansson (Natasha Romanoff / Black Widow)

Andrew Garfield (Peter Parker / Spider-Man)

Lauren Ridloff (Makkari)

May Calamawy (Layla El-Faouly / Scarlet Scarab)

Emilia Clarke (G'iah)

Jeffrey Wright (The Watcher)

Harrison Ford (Thaddeus "Thunderbolt" Ross)

Olga Kurylenko (Antonia Dreykov / Taskmaster)

Brett Goldstein (Hercules)

Don Lee (Gilgamesh)

94

92

91

90

89

88

87

86

85

84

83

82

81

79

78

76

75

74

73

72

70

69

66

65

62

59

54

53

52

50

48

46

42

41

34

32

27

19

17

16

If Artificial General Intelligence has an okay outcome, what will be the reason?

Jun 22, 6:46 PMJan 1, 4:59 AM

132634