The Quantum Mars Teleporter: An Empirical Test Of Personal Identity Theories

avturchin22 Jan 2025 11:48 UTC

6 points

0 comments2 min readLW link

Bayesian Reasoning on Maps

Sjlver22 Jan 2025 10:45 UTC

2 points

0 comments4 min readLW link

(blog.purpureus.net)

Against blanket arguments against interpretability

Dmitry Vaintrob22 Jan 2025 9:46 UTC

21 points

1 comment7 min readLW link

February 2025 meetup

jn222 Jan 2025 9:41 UTC

1 point

0 comments1 min readLW link

The real political spectrum

Hzn22 Jan 2025 8:55 UTC

−4 points

0 comments1 min readLW link

Evolution and the Low Road to Nash

Aydin Mohseni, ben_levinstein and Daniel Herrmann

22 Jan 2025 7:06 UTC

5 points

0 comments9 min readLW link

The Human Alignment Problem for AIs

rife22 Jan 2025 4:06 UTC

6 points

4 comments3 min readLW link

When does capability elicitation bound risk?

joshc22 Jan 2025 3:42 UTC

5 points

0 comments17 min readLW link

(redwoodresearch.substack.com)

[Question] Popular materials about environmental goals/agent foundations? People wanting to discuss such topics?

Q Home22 Jan 2025 3:30 UTC

5 points

0 comments1 min readLW link

Kitchen Air Purifier Comparison

jefftk22 Jan 2025 3:20 UTC

27 points

2 comments3 min readLW link

(www.jefftk.com)

November-December 2024 Progress in Guaranteed Safe AI

Quinn22 Jan 2025 1:20 UTC

16 points

0 comments4 min readLW link

(gsai.substack.com)

Quotes from the Stargate press conference

Nikola Jurkovic22 Jan 2025 0:50 UTC

108 points

1 comment1 min readLW link

(www.c-span.org)

Tell me about yourself: LLMs are aware of their implicit behaviors

Martín Soto and Owain_Evans

22 Jan 2025 0:47 UTC

56 points

0 comments6 min readLW link

(bit.ly)

Using the probabilistic method to bound the performance of toy transformers

Alex Gibson21 Jan 2025 23:01 UTC

1 point

0 comments3 min readLW link

Austin LW Online Meetup/Game Night, 1/21/2025

SilasBarta21 Jan 2025 22:17 UTC

8 points

0 comments1 min readLW link

Training on Documents About Reward Hacking Induces Reward Hacking

evhub21 Jan 2025 21:32 UTC

83 points

7 comments2 min readLW link

(alignment.anthropic.com)

Veo-2 Can Produce Realistic Ads

Logan Riggs21 Jan 2025 19:13 UTC

12 points

0 comments1 min readLW link

Computational Limits on Efficiency

vibhumeh21 Jan 2025 18:29 UTC

1 point

0 comments5 min readLW link

Democratizing AI Governance: Balancing Expertise and Public Participation

Lucile Ter-Minassian21 Jan 2025 18:29 UTC

1 point

0 comments15 min readLW link

Hitler was not a monster

halgir21 Jan 2025 18:21 UTC

−3 points

0 comments1 min readLW link