RL, but don’t do anything I wouldn’t do

Gunnar_Zarncke7 Dec 2024 22:54 UTC

22 points

0 comments1 min readLW link

(arxiv.org)

Mask and Respirator Intelligibility Comparison

jefftk7 Dec 2024 3:20 UTC

16 points

1 comment1 min readLW link

(www.jefftk.com)

Broadening Horizons: Rethinking Social Mobility Through Skill Diversification

Yanling Guo7 Dec 2024 0:04 UTC

−1 points

0 comments2 min readLW link

Purging Corrupted Capabilities across Language Models

Amirali Abdullah, Narmeen, Dhruv Nathawani and nirmalendu prakash

6 Dec 2024 22:56 UTC

8 points

0 comments16 min readLW link

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks

cloud, Jacob G-W, Evzen, Joseph Miller and TurnTrout

6 Dec 2024 22:19 UTC

98 points

1 comment11 min readLW link

(arxiv.org)

Understanding Shapley Values with Venn Diagrams

agucova6 Dec 2024 21:56 UTC

70 points

5 comments1 min readLW link

(medium.com)

Model Integrity

ryan.lowe, Oliver Klingefjord and Joe Edelman

6 Dec 2024 21:28 UTC

4 points

1 comment18 min readLW link

Can AI improve the current state of molecular simulation?

Abhishaike Mahajan6 Dec 2024 20:22 UTC

4 points

0 comments1 min readLW link

(www.owlposting.com)

Low Temperature Solomonoff Induction

dil-leik-og6 Dec 2024 18:55 UTC

2 points

0 comments11 min readLW link

Experiments are in the territory, results are in the map

Tahp6 Dec 2024 15:44 UTC

7 points

1 comment6 min readLW link

Frontier Models are Capable of In-context Scheming

Marius Hobbhahn, AlexMeinke, Bronson Schoen, rusheb, Jérémy Scheurer and Mikita Balesni

5 Dec 2024 22:11 UTC

170 points

12 comments7 min readLW link

Are SAE features from the Base Model still meaningful to LLaVA?

Shan23Chen5 Dec 2024 20:21 UTC

6 points

0 comments10 min readLW link

(www.lesswrong.com)

Expevolu, a laissez-faire approach to country creation

Fernando5 Dec 2024 19:29 UTC

2 points

2 comments43 min readLW link

(expevolu.substack.com)

Are SAE features from the Base Model still meaningful to LLaVA?

Shan23Chen5 Dec 2024 19:24 UTC

4 points

0 comments10 min readLW link

Smart people should do biology

Haotian Huang5 Dec 2024 19:11 UTC

7 points

2 comments3 min readLW link

Detection of Asymptomatically Spreading Pathogens

jefftk5 Dec 2024 18:20 UTC

45 points

7 comments7 min readLW link

(www.jefftk.com)

Model Integrity: MAI on Value Alignment

Jonas Hallgren5 Dec 2024 17:11 UTC

6 points

11 comments1 min readLW link

(meaningalignment.substack.com)

Social Science in its epistemological context

Arturo Macias5 Dec 2024 16:12 UTC

2 points

0 comments1 min readLW link

(www.theseedsofscience.pub)

Why muscle tension can be unsexy

Chipmonk5 Dec 2024 16:11 UTC

8 points

9 comments1 min readLW link

(chrislakin.blog)

What If We Rebuild Motivation with the Fermi ESTIMATion?

Gabriel Brito5 Dec 2024 15:35 UTC

5 points

0 comments4 min readLW link