Reinforcement Learning, Agency and Taste

epicurus12 May 2026 18:22 UTC

7 points

0 comments9 min readLW link

The Owned Ones

Eliezer Yudkowsky12 May 2026 17:56 UTC

180 points

23 comments6 min readLW link

Signaling and Perverse Adoption of Expensive AI

Adam Chlipala12 May 2026 14:34 UTC

−21 points

2 comments8 min readLW link

On Having Good Hot Takes

Celer12 May 2026 14:20 UTC

9 points

0 comments8 min readLW link

(keller.substack.com)

Optimisation: Selective versus Predictive

Raymond Douglas12 May 2026 14:03 UTC

63 points

6 comments3 min readLW link

The Lies and Fallacies of the Buyer and Seller

Hide12 May 2026 11:26 UTC

24 points

16 comments16 min readLW link

(hidefromit.substack.com)

When should an AI incident trigger an international response? Criteria for international escalation and implications for the design of AI incident frameworks

Josephine Schwab, Francesca Gomez, Mike Harre, Matthew Ball and Lydia Preston

12 May 2026 8:52 UTC

12 points

0 comments4 min readLW link

Verbalised evaluation awareness in language models has little effect on their behaviour

Amelie Knecht, lucas-florin and Thilo Hagendorff

12 May 2026 5:36 UTC

10 points

0 comments6 min readLW link

The terrible weight of seeing the board

philosophybear12 May 2026 5:13 UTC

1 point

7 comments9 min readLW link

Fibonacci Structure in Harmonic Series Partitions

Avyukth Nilajagi12 May 2026 4:26 UTC

5 points

1 comment2 min readLW link

Our experience of the first research in a project incubator: much more than you wanted to know

Ivan Belashkin and Iosif Polozov

11 May 2026 20:28 UTC

2 points

0 comments10 min readLW link

I don’t have questions: how a good Jewish boy turns atheist

Semi-Pseudonymous11 May 2026 20:11 UTC

20 points

1 comment6 min readLW link

Where are all the Decision Markets?

alexjaniak11 May 2026 19:48 UTC

11 points

2 comments3 min readLW link

RFDiffusion3: A Brief Exploration

michaelwaves11 May 2026 19:26 UTC

3 points

0 comments5 min readLW link

On Clouds and Atlases

pbennett11 May 2026 19:23 UTC

0 points

0 comments15 min readLW link

(chasingsunsets.dev)

Childhood And Education #17: Is Our Children Reading

Zvi11 May 2026 19:10 UTC

39 points

1 comment15 min readLW link

(thezvi.wordpress.com)

The Iliad Intensive Course Materials

Leon Lang, David Udell and Alexander Gietelink Oldenziel

11 May 2026 18:55 UTC

135 points

0 comments13 min readLW link

(docs.google.com)

[Linkpost] Language Models Can Autonomously Hack and Self-Replicate

Gunnar_Zarncke11 May 2026 18:16 UTC

15 points

0 comments1 min readLW link

Empowerment, corrigibility, etc. are simple abstractions (of a messed-up ontology)

Steven Byrnes11 May 2026 17:48 UTC

98 points

35 comments16 min readLW link

A Field Guide To Learning

sonicrocketman11 May 2026 17:12 UTC

5 points

0 comments4 min readLW link