Modifying LLM Beliefs with Synthetic Document Finetuning

RowanWang, Johannes Treutlein, Ethan Perez, Fabien Roger and Sam Marks

24 Apr 2025 21:15 UTC

52 points

2 comments2 min readLW link

(alignment.anthropic.com)

“The Era of Experience” has an unsolved technical alignment problem

Steven Byrnes24 Apr 2025 13:57 UTC

65 points

5 comments23 min readLW link

To Understand History, Keep Former Population Distributions In Mind

Arjun Panickssery23 Apr 2025 4:51 UTC

174 points

6 comments2 min readLW link

(arjunpanickssery.substack.com)

A review of “Why Did Environmentalism Become Partisan?”

David Scott Krueger (formerly: capybaralet)25 Apr 2025 5:12 UTC

7 points

0 comments4 min readLW link

Reward hacking is becoming more sophisticated and deliberate in frontier LLMs

Kei24 Apr 2025 16:03 UTC

35 points

3 comments1 min readLW link

Token and Taboo

Guive24 Apr 2025 20:17 UTC

30 points

3 comments4 min readLW link

(guive.substack.com)

Accountability Sinks

Martin Sustrik22 Apr 2025 5:00 UTC

230 points

20 comments15 min readLW link

(250bpm.substack.com)

Training-time schemers vs behavioral schemers

Alex Mallen24 Apr 2025 19:07 UTC

22 points

0 comments6 min readLW link

Jaan Tallinn’s 2024 Philanthropy Overview

jaan23 Apr 2025 11:06 UTC

120 points

5 comments1 min readLW link

(jaan.info)

The Intelligence Curse: an essay series

L Rudolf L and lukedrago

24 Apr 2025 12:59 UTC

34 points

2 comments2 min readLW link

o3 Is a Lying Liar

Zvi23 Apr 2025 20:00 UTC

72 points

16 comments9 min readLW link

(thezvi.wordpress.com)

OpenAI Alums, Nobel Laureates Urge Regulators to Save Company’s Nonprofit Structure

garrison23 Apr 2025 23:01 UTC

57 points

0 comments LW link

(garrisonlovely.substack.com)

My Favorite Productivity Blog Posts

Parker Conley24 Apr 2025 0:32 UTC

41 points

0 comments1 min readLW link

(parconley.com)

AI #113: The o3 Era Begins

Zvi24 Apr 2025 13:40 UTC

24 points

2 comments62 min readLW link

(thezvi.wordpress.com)

Why Should I Assume CCP AGI is Worse Than USG AGI?

Tomás B.19 Apr 2025 14:47 UTC

219 points

69 comments1 min readLW link

Finding an Error-Detection Feature in DeepSeek-R1

keith_wynroe24 Apr 2025 16:03 UTC

9 points

0 comments7 min readLW link

Putting up Bumpers

Sam Bowman23 Apr 2025 16:05 UTC

43 points

13 comments2 min readLW link

Personal evaluation of LLMs, through chess

Karthik Tadepalli24 Apr 2025 7:01 UTC

19 points

3 comments2 min readLW link

Academia as a happy place?

jow and pchvykov

24 Apr 2025 14:03 UTC

9 points

0 comments19 min readLW link

Severe control over AI agents as a tool for mass-surveillance

Andrey Seryakov24 Apr 2025 20:27 UTC

1 point

0 comments3 min readLW link