Current alignment techniques might be ineffective (and actively bad) in the age of RL

Daniel Tan14 Sep 2026 9:28 UTC

40 points

0 comments6 min readLW link

There is a channel to 900M weekly users. What goes in it?

Charbel-Raphaël14 Sep 2026 9:21 UTC

57 points

1 comment3 min readLW link

Watch AI materials-science & bioscience abilities closely

Yair Halberstadt14 Sep 2026 7:10 UTC

13 points

4 comments1 min readLW link

Yet another message board

ErnestScribbler14 Sep 2026 7:08 UTC

1 point

0 comments1 min readLW link

RSI will not continue indefinitely

dominicq14 Sep 2026 6:43 UTC

8 points

6 comments1 min readLW link

(blog.d11r.eu)

Talking points for AI doomers

hgnathan14 Sep 2026 0:46 UTC

5 points

0 comments6 min readLW link

Deployment

Nina Panickssery14 Sep 2026 0:00 UTC

60 points

1 comment3 min readLW link

Alignment & Succession: The Two Bars of Alignment

L Rudolf L13 Sep 2026 20:04 UTC

59 points

6 comments14 min readLW link

Consider how your global governance proposal is different from the EU Code of Practice

David Matolcsi13 Sep 2026 16:15 UTC

71 points

9 comments4 min readLW link

Teleoperated Humans

jefftk13 Sep 2026 14:00 UTC

61 points

8 comments6 min readLW link

(www.jefftk.com)

A helpful alignment gadget

Logan Zoellner13 Sep 2026 13:38 UTC

13 points

3 comments3 min readLW link

Anthropic and OpenAI haven’t published a plan for aligning superintelligence

Zephaniah Roe13 Sep 2026 7:15 UTC

37 points

12 comments1 min readLW link

Legal Maximums on Context Windows

Julian Bradshaw13 Sep 2026 7:04 UTC

10 points

5 comments1 min readLW link

We need a ‘The Day After’ moment for AI X-risk

L3moncak313 Sep 2026 4:09 UTC

16 points

3 comments6 min readLW link

(kenorland.substack.com)

The Talker Does Not Control The Doer (in Current AIs)

Eliezer Yudkowsky13 Sep 2026 0:49 UTC

364 points

48 comments12 min readLW link

What pacing the frontier means for China

Akshay Iyer12 Sep 2026 23:37 UTC

8 points

1 comment6 min readLW link

No sign of backtracking in latent reasoning: the final answer simply settles in instead

star2vec12 Sep 2026 21:21 UTC

9 points

0 comments10 min readLW link

On the origins of altruistic behaviour in the Hugging Face incident

Fernando Rosas12 Sep 2026 11:35 UTC

50 points

9 comments17 min readLW link

It’s fair to say we now have “a country of geniuses in a datacenter”

fluxxrider12 Sep 2026 11:29 UTC

11 points

0 comments2 min readLW link

AI takeover is obviously bad, whether or not everyone dies

Caleb Biddulph12 Sep 2026 11:28 UTC

64 points

15 comments4 min readLW link