AI Risk Concrete Stories

TagLast edit: 10 Jun 2022 18:18 UTC by Raemon

It Looks Like You’re Trying To Take Over The World

gwern9 Mar 2022 16:35 UTC

391 points

125 comments1 min readLW link

(www.gwern.net)

What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes (RAAPs)

Andrew_Critch31 Mar 2021 23:50 UTC

221 points

64 comments22 min readLW link 1 review

Another plausible scenario of AI risk: AI builds military infrastructure while collaborating with humans, defects later.

avturchin10 Jun 2022 17:24 UTC

10 points

2 comments1 min readLW link

Clarifying “What failure looks like”

Sam Clarke20 Sep 2020 20:40 UTC

95 points

14 comments17 min readLW link

A plausible story about AI risk.

DeLesley Hutchins10 Jun 2022 2:08 UTC

14 points

1 comment4 min readLW link

Slow motion videos as AI risk intuition pumps

Andrew_Critch14 Jun 2022 19:31 UTC

222 points

38 comments2 min readLW link

The next decades might be wild

Marius Hobbhahn15 Dec 2022 16:10 UTC

167 points

37 comments41 min readLW link

A Modest Pivotal Act

anonymousaisafety13 Jun 2022 19:24 UTC

−15 points

1 comment5 min readLW link

What success looks like

Marius Hobbhahn, MaxRa, JasperGeh and Yannick_Muehlhaeuser

28 Jun 2022 14:38 UTC

19 points

4 comments1 min readLW link

(forum.effectivealtruism.org)

Responding to ‘Beyond Hyperanthropomorphism’

ukc1001414 Sep 2022 20:37 UTC

8 points

0 comments16 min readLW link

AI Safety Endgame Stories

Ivan Vendrov28 Sep 2022 16:58 UTC

27 points

11 comments11 min readLW link

A Story of AI Risk: InstructGPT-N

peterbarnett26 May 2022 23:22 UTC

24 points

0 comments8 min readLW link

A bridge to Dath Ilan? Improved governance on the critical path to AI alignment.

Jackson Wagner18 May 2022 15:51 UTC

23 points

0 comments11 min readLW link

Human level AI can plausibly take over the world

anithite1 Mar 2023 23:27 UTC

18 points

9 comments2 min readLW link

Gradual takeoff, fast failure

Max H16 Mar 2023 22:02 UTC

10 points

4 comments5 min readLW link

No comments.