Conditioning Predictive Models: The case for competitiveness

evhub, Adam Jermyn, Johannes Treutlein, Rubi J. Hudson and kcwoolverton

6 Feb 2023 20:08 UTC

18 points

0 comments11 min readLW link

Why Theorems? A Brief Defence

DragonGod6 Feb 2023 17:43 UTC

11 points

9 comments2 min readLW link

Childhoods of exceptional people

Henrik Karlsson6 Feb 2023 17:27 UTC

76 points

10 comments15 min readLW link

(escapingflatland.substack.com)

Foodpairing and Embeddings

jurabrazdil6 Feb 2023 15:09 UTC

12 points

2 comments5 min readLW link

Oversight and AI risk [MLAISU W05]

Esben Kran and Fazl

6 Feb 2023 12:26 UTC

4 points

0 comments2 min readLW link

(newsletter.apartresearch.com)

Project Idea: Lots of Cause-area-specific Online Unconferences

Linda Linsefors6 Feb 2023 11:05 UTC

26 points

1 comment1 min readLW link

Decision Transformer Interpretability

Joseph Bloom and Paul Colognese

6 Feb 2023 7:29 UTC

59 points

0 comments24 min readLW link

Why is Everyone So Boring? By Robin Hanson

Trevor16 Feb 2023 4:17 UTC

45 points

9 comments1 min readLW link

(www.overcomingbias.com)

Gradient surfing: the hidden role of regularization

Jesse Hoogland6 Feb 2023 3:50 UTC

24 points

6 comments5 min readLW link

(www.jessehoogland.com)

Why Are Bacteria So Simple?

aysja6 Feb 2023 3:00 UTC

102 points

14 comments10 min readLW link

The Law of Identity

Chris_Leong6 Feb 2023 2:59 UTC

6 points

5 comments3 min readLW link

Robin Hanson on “Explaining the Sacred”

Raemon6 Feb 2023 0:50 UTC

11 points

3 comments3 min readLW link

(www.overcomingbias.com)

Interview Daniel Murfet on Universal Phenomena in Learning Machines

Alexander Gietelink Oldenziel6 Feb 2023 0:00 UTC

25 points

1 comment16 min readLW link

SolidGoldMagikarp (plus, prompt generation)

Jessica Rumbelow and mwatkins

5 Feb 2023 22:02 UTC

422 points

98 comments12 min readLW link

Are short timelines actually bad?

joshc5 Feb 2023 21:21 UTC

45 points

6 comments3 min readLW link

A List of things I might do with a Proof Oracle

Logan Zoellner5 Feb 2023 18:14 UTC

−9 points

12 comments3 min readLW link

Control

TsviBT5 Feb 2023 16:16 UTC

17 points

3 comments9 min readLW link

A BOTEC estimating the effects of an AI capabilities project on AI timelines, unaligned AI, and human extinction

WilliamKiely5 Feb 2023 11:26 UTC

−1 points

3 comments7 min readLW link

Research Direction: Be the AGI you want to see in the world

scottviteri, sudo -i and Lauro Langosco

5 Feb 2023 7:15 UTC

34 points

0 comments7 min readLW link

Sex is Good, Actually

Gordon Seidoh Worley5 Feb 2023 6:33 UTC

25 points

8 comments4 min readLW link