$500 Bounty Problem: Are (Approximately) Deterministic Natural Latents All You Need?

johnswentworth and David Lorell

21 Apr 2025 20:19 UTC

67 points

1 comment3 min readLW link

More Than Just A, T, C, and G: Screening for Hidden Dangers in DNA Sequences

sgd21 Apr 2025 20:12 UTC

1 point

0 comments11 min readLW link

Podcast on “AI tools for existential security” — transcript

21 Apr 2025 19:26 UTC

11 points

0 comments43 min readLW link

(pnc.st)

Implications for the likelihood of human extinction from the recent discovery of possible microbial life

Mvolz21 Apr 2025 19:15 UTC

2 points

2 comments1 min readLW link

Key event tracker for AI2027

MarkelKori21 Apr 2025 19:02 UTC

1 point

0 comments1 min readLW link

The Uses of Complacency

sarahconstantin21 Apr 2025 18:50 UTC

50 points

3 comments8 min readLW link

(sarahconstantin.substack.com)

Feature-Based Analysis of Safety-Relevant Multi-Agent Behavior

Maria Kapros, Ana Kapros and Perusha Moodley

21 Apr 2025 18:12 UTC

1 point

0 comments5 min readLW link

Crime and Punishment #1

Zvi21 Apr 2025 15:30 UTC

37 points

4 comments39 min readLW link

(thezvi.wordpress.com)

Improving CNNs with Klein Networks: A Topological Approach to AI

Gunnar Carlsson21 Apr 2025 15:21 UTC

17 points

4 comments5 min readLW link

Eulogy to the Obits

Niko_McCarty and xanderbalwit

21 Apr 2025 14:10 UTC

2 points

0 comments10 min readLW link

Research Notes: Running Claude 3.7, Gemini 2.5 Pro, and o3 on Pokémon Red

Julian Bradshaw21 Apr 2025 3:52 UTC

88 points

10 comments14 min readLW link

Not All Beliefs Are Created Equal: Diagnosing Toxic Ideologies

Big_friendly_kiwi21 Apr 2025 3:18 UTC

14 points

5 comments9 min readLW link

AI 2027 is a Bet Against Amdahl’s Law

snewman21 Apr 2025 3:09 UTC

101 points

26 comments9 min readLW link

Severance and the Ethics of the Conscious Agents

Crissman21 Apr 2025 2:21 UTC

3 points

0 comments1 min readLW link

March-April 2025 Progress in Guaranteed Safe AI

Quinn20 Apr 2025 19:00 UTC

6 points

0 comments4 min readLW link

(gsai.substack.com)

How to end credentialism

Yair Halberstadt20 Apr 2025 18:50 UTC

13 points

14 comments8 min readLW link

Spending on Ourselves

jefftk20 Apr 2025 18:40 UTC

21 points

0 comments3 min readLW link

(www.jefftk.com)

Interesting ACX 2024 Book Review Entries

jenn20 Apr 2025 18:10 UTC

23 points

1 comment4 min readLW link

[Question] To what ethics is an AGI actually safely alignable?

StanislavKrym20 Apr 2025 17:09 UTC

1 point

6 comments4 min readLW link

Evaluating Oversight Robustness with Incentivized Reward Hacking

Yoav, Juan V, julianjm and McKennaFitzgerald

20 Apr 2025 16:53 UTC

1 point

0 comments15 min readLW link