rosehadshar

Karma: 726

New report: A review of the empirical evidence for existential risk from AI via misaligned power-seeking

Harlan and rosehadshar

4 Apr 2024 23:41 UTC

31 points

5 comments1 min readLW link

(blog.aiimpacts.org)

Results from an Adversarial Collaboration on AI Risk (FRI)

Josh Rosenberg, AvitalM, Molly and rosehadshar

11 Mar 2024 20:00 UTC

60 points

3 comments9 min readLW link

(forecastingresearch.org)

[Question] Strongest real-world examples supporting AI risk claims?

rosehadshar5 Sep 2023 15:12 UTC

41 points

7 comments1 min readLW link

Short timelines and slow, continuous takeoff as the safest path to AGI

rosehadshar and Alex Lintz

21 Jun 2023 8:56 UTC

64 points

15 comments7 min readLW link

The self-unalignment problem

Jan_Kulveit and rosehadshar

14 Apr 2023 12:10 UTC

146 points

24 comments10 min readLW link

Why Simulator AIs want to be Active Inference AIs

Jan_Kulveit and rosehadshar

10 Apr 2023 18:23 UTC

91 points

8 comments8 min readLW link

Current UK government levers on AI development

rosehadshar10 Apr 2023 13:16 UTC

16 points

0 comments1 min readLW link

Lessons from Convergent Evolution for AI Alignment

Jan_Kulveit and rosehadshar

27 Mar 2023 16:25 UTC

54 points

9 comments8 min readLW link

The space of systems and the space of maps

Jan_Kulveit, rosehadshar, Nora_Ammann and clem_acs

22 Mar 2023 14:59 UTC

39 points

0 comments5 min readLW link

Cyborg Periods: There will be multiple AI transitions

Jan_Kulveit and rosehadshar

22 Feb 2023 16:09 UTC

108 points

9 comments6 min readLW link

What’s going on with ‘crunch time’?

rosehadshar20 Jan 2023 9:42 UTC

53 points

6 comments4 min readLW link

Internal communication framework

rosehadshar and Nora_Ammann

15 Nov 2022 12:41 UTC

38 points

13 comments12 min readLW link

The economy as an analogy for advanced AI systems

rosehadshar and particlemania

15 Nov 2022 11:16 UTC

28 points

0 comments5 min readLW link