From seeded complexity to consciousness—yes, it’s all the same.

eschatail8 Oct 2024 21:31 UTC

0 points

0 comments2 min readLW link

Limits of safe and aligned AI

Shivam8 Oct 2024 21:30 UTC

1 point

0 comments4 min readLW link

[Question] What constitutes an infohazard?

K1r4d4rk.v18 Oct 2024 21:29 UTC

0 points

3 comments1 min readLW link

[Intuitive self-models] 4. Trance

Steven Byrnes8 Oct 2024 13:30 UTC

26 points

2 comments25 min readLW link

Schelling game evaluations for AI control

Olli Järviniemi8 Oct 2024 12:01 UTC

44 points

0 comments11 min readLW link

Overview of strong human intelligence amplification methods

TsviBT8 Oct 2024 8:37 UTC

122 points

43 comments10 min readLW link

Simulating near-death experiences

Declan Molony8 Oct 2024 6:34 UTC

4 points

1 comment3 min readLW link

The unreasonable effectiveness of plasmid sequencing as a service

Abhishaike Mahajan8 Oct 2024 2:02 UTC

22 points

0 comments13 min readLW link

(www.owlposting.com)

There is a globe in your LLM

jacob_drori8 Oct 2024 0:43 UTC

44 points

0 comments1 min readLW link

MATS AI Safety Strategy Curriculum v2

DanielFilan and Ryan Kidd

7 Oct 2024 22:44 UTC

38 points

4 comments13 min readLW link

2025 Color Trends

sarahconstantin7 Oct 2024 21:20 UTC

29 points

4 comments6 min readLW link

(sarahconstantin.substack.com)

Clarifying Alignment Fundamentals Through the Lens of Ontology

eternal/ephemera7 Oct 2024 20:57 UTC

10 points

0 comments24 min readLW link

Ethics on Cosmic Scale, Outer Space Treaty, Directed Panspermia, Forwards-Contamination, Technology Assessment, Planetary Protection, and Fermi’s Paradox

MrFantastic7 Oct 2024 20:56 UTC

−5 points

0 comments1 min readLW link

Domain-specific SAEs

jacob_drori7 Oct 2024 20:15 UTC

22 points

0 comments5 min readLW link

Research update: Towards a Law of Iterated Expectations for Heuristic Estimators

Eric Neyman7 Oct 2024 19:29 UTC

75 points

2 comments22 min readLW link

AI Model Registries: A Foundational Tool for AI Governance

Elliot Mckernon, Deric Cheng and Gwyn Glasser

7 Oct 2024 19:27 UTC

20 points

1 comment4 min readLW link

(www.convergenceanalysis.org)

Evaluating the truth of statements in a world of ambiguous language.

Hastings7 Oct 2024 18:08 UTC

44 points

17 comments2 min readLW link

Advice for journalists

Nathan Young7 Oct 2024 16:46 UTC

48 points

15 comments9 min readLW link

(nathanpmyoung.substack.com)

Time Efficient Resistance Training

romeostevensit7 Oct 2024 15:15 UTC

38 points

5 comments3 min readLW link

A Narrow Path: a plan to deal with AI extinction risk

Andrea_Miotti, davekasten and Tolga

7 Oct 2024 13:02 UTC

73 points

8 comments2 min readLW link

(www.narrowpath.co)