1a3orn

Karma: 3,669

1a3orn’s Shortform

1a3orn5 Jan 2024 15:04 UTC

5 points

7 comments1 min readLW link

Propaganda or Science: A Look at Open Source AI and Bioterrorism Risk

1a3orn2 Nov 2023 18:20 UTC

191 points

79 comments23 min readLW link

Ways I Expect AI Regulation To Increase Extinction Risk

1a3orn4 Jul 2023 17:32 UTC

210 points

32 comments7 min readLW link

Yudkowsky vs Hanson on FOOM: Whose Predictions Were Better?

1a3orn1 Jun 2023 19:36 UTC

132 points

73 comments24 min readLW link

Giant (In)scrutable Matrices: (Maybe) the Best of All Possible Worlds

1a3orn4 Apr 2023 17:39 UTC

191 points

35 comments5 min readLW link

[Question] What is a good comprehensive examination of risks near the Ohio train derailment?

1a3orn16 Mar 2023 0:21 UTC

17 points

0 comments1 min readLW link

Parameter Scaling Comes for RL, Maybe

1a3orn24 Jan 2023 13:55 UTC

98 points

3 comments14 min readLW link

“A Generalist Agent”: New DeepMind Publication

1a3orn12 May 2022 15:30 UTC

79 points

43 comments1 min readLW link

New Scaling Laws for Large Language Models

1a3orn1 Apr 2022 20:41 UTC

243 points

22 comments5 min readLW link

EfficientZero: How It Works

1a3orn26 Nov 2021 15:17 UTC

292 points

50 comments29 min readLW link 1 review

Jitters No Evidence of Stupidity in RL

1a3orn16 Sep 2021 22:43 UTC

96 points

18 comments3 min readLW link

How DeepMind’s Generally Capable Agents Were Trained

1a3orn20 Aug 2021 18:52 UTC

87 points

6 comments19 min readLW link

Coase’s “Nature of the Firm” on Polyamory

1a3orn13 Aug 2021 13:15 UTC

101 points

34 comments1 min readLW link 2 reviews

Promoting Prediction Markets With Meaningless Internet-Point Badges

1a3orn8 Feb 2021 19:03 UTC

59 points

21 comments2 min readLW link