The Future of Aligning Deep Learning systems will probably look like “training on interp”

williawa20 Mar 2026 23:06 UTC

8 points

1 comment4 min readLW link

An agent autonomously builds a 1.5 GHz Linux-capable RISC-V CPU

sanxiyn20 Mar 2026 23:03 UTC

16 points

0 comments2 min readLW link

(arxiv.org)

Untrusted monitoring: extra bits

Morgan S20 Mar 2026 21:32 UTC

7 points

0 comments15 min readLW link

Finding features in Transformers: Contrastive directions elicit stronger low-level perturbation responses than baselines

Francisco Ferreira da Silva and StefanHex

20 Mar 2026 21:09 UTC

18 points

1 comment6 min readLW link

ARENA 7.0 Impact Report

JScriven and JamesH

20 Mar 2026 17:09 UTC

7 points

0 comments21 min readLW link

The Federal AI Policy Framework: An Improvement, But My Offer Is (Still Almost) Nothing

Zvi20 Mar 2026 16:51 UTC

20 points

0 comments8 min readLW link

(thezvi.wordpress.com)

Confusion around the term reward hacking

ariana_azarbal20 Mar 2026 16:13 UTC

29 points

5 comments5 min readLW link

The Distaff Texts

Tomás B.20 Mar 2026 15:05 UTC

44 points

1 comment14 min readLW link

It’s a Good Thing to Respond to Internet Trolls

Bowl of Cereal20 Mar 2026 14:22 UTC

1 point

2 comments2 min readLW link

Untrusted Monitoring is Default; Trusted Monitoring is not

J Bostock20 Mar 2026 14:10 UTC

19 points

0 comments4 min readLW link

Against Messianic AI: Why Optimizing the Environment Doesn’t Optimize the Agent

Nathan Heath20 Mar 2026 12:40 UTC

−3 points

0 comments3 min readLW link

2nd (Unofficial) ACX Weekend

Fernand020 Mar 2026 12:13 UTC

1 point

0 comments1 min readLW link

Why I am not buying IPv4 addresses as an investment

samuelshadrach20 Mar 2026 9:02 UTC

5 points

1 comment5 min readLW link

(samuelshadrach.com)

Hundred ways a superintelligence could kill you (non-serious exercise)

samuelshadrach20 Mar 2026 8:58 UTC

2 points

1 comment6 min readLW link

(samuelshadrach.com)

Internet anonymity without Tor

samuelshadrach20 Mar 2026 8:52 UTC

3 points

0 comments3 min readLW link

(samuelshadrach.com)

No, You Don’t Need Self-Locating Evidence.

Ape in the coat20 Mar 2026 5:38 UTC

9 points

2 comments5 min readLW link

(substack.com)

The Low Hanging Fruit of AI Self Improvement

HunterJay20 Mar 2026 4:09 UTC

1 point

0 comments5 min readLW link

Nullius in Verba

Aurelia20 Mar 2026 3:19 UTC

90 points

10 comments12 min readLW link

Does Hebrew Have Verbs?

Benquo20 Mar 2026 3:04 UTC

27 points

4 comments6 min readLW link

Positive-sum interactions between players with linear utility in resources

Cleo Nardo20 Mar 2026 0:42 UTC

10 points

0 comments2 min readLW link