TurnTrout

Karma: 24,350

I don’t use LessWrong much anymore. Find me at www.turntrout.com.

My name is Alex Turner. Reach me at alex@turntrout.com :)

A Red Line and Oversight Framework for Government AI Contracts

TurnTrout18 Jul 2026 18:58 UTC

51 points

0 comments29 min readLW link

(turntrout.com)

Why I Left Google DeepMind

TurnTrout15 Jul 2026 17:42 UTC

1,066 points

43 comments36 min readLW link

(turntrout.com)

How robust are natural language autoencoders to initialization?

michaelzhang and TurnTrout

10 Jul 2026 0:40 UTC

82 points

3 comments13 min readLW link

(turntrout.com)

LessWrong Shows You Social Signals Before the Comment

TurnTrout28 Apr 2026 0:30 UTC

175 points

33 comments4 min readLW link

punctilio: the best text prettifier

TurnTrout11 Feb 2026 4:49 UTC

24 points

0 comments5 min readLW link

(github.com)

No instrumental convergence without AI psychology

TurnTrout20 Jan 2026 22:16 UTC

68 points

7 comments6 min readLW link

(turntrout.com)

Apply for Alignment Mentorship from TurnTrout and Alex Cloud

TurnTrout and cloud

26 Dec 2025 17:20 UTC

42 points

0 comments2 min readLW link

(turntrout.com)

2025-Era “Reward Hacking” Does Not Show that Reward Is the Optimization Target

TurnTrout19 Dec 2025 6:09 UTC

49 points

9 comments7 min readLW link

(turntrout.com)

Automatic alt text generation

TurnTrout22 Nov 2025 17:57 UTC

27 points

1 comment1 min readLW link

(turntrout.com)

[Paper] Output Supervision Can Obfuscate the CoT

jacob_drori, lukemarks, cloud and TurnTrout

20 Nov 2025 22:41 UTC

92 points

3 comments5 min readLW link

(arxiv.org)

GDM: Consistency Training Helps Limit Sycophancy and Jailbreaks in Gemini 2.5 Flash

TurnTrout and Rohin Shah

4 Nov 2025 16:25 UTC

55 points

2 comments6 min readLW link

(arxiv.org)

An Opinionated Guide to Privacy Despite Authoritarianism

TurnTrout29 Oct 2025 20:32 UTC

181 points

31 comments4 min readLW link

(turntrout.com)

Recontextualization Mitigates Specification Gaming Without Modifying the Specification

ariana_azarbal, Victor Gillioz, TurnTrout and cloud

14 Oct 2025 0:53 UTC

145 points

15 comments10 min readLW link

Training a Reward Hacker Despite Perfect Labels

ariana_azarbal, Victor Gillioz and TurnTrout

14 Aug 2025 23:57 UTC

142 points

47 comments4 min readLW link

[Research Note] Optimizing The Final Output Can Obfuscate CoT

lukemarks, jacob_drori, cloud and TurnTrout

30 Jul 2025 21:26 UTC

203 points

23 comments6 min readLW link

English writes numbers backwards

TurnTrout25 Jul 2025 23:00 UTC

15 points

23 comments12 min readLW link

(turntrout.com)

We Built a Tool to Protect Your Dataset From Simple Scrapers

TurnTrout, Edward Turner, Roy Rinberg and Dipika Khullar

25 Jul 2025 5:44 UTC

65 points

9 comments3 min readLW link

A Simple Explanation of AGI Risk

TurnTrout1 Jul 2025 16:18 UTC

58 points

4 comments5 min readLW link

(turntrout.com)

Authors Have a Responsibility to Communicate Clearly

TurnTrout1 Jul 2025 15:41 UTC

127 points

29 comments6 min readLW link

(turntrout.com)

Distillation Robustifies Unlearning

Bruce W. Lee, Addie Foote, alexinf, leni, Jacob G-W, Harish Kamath, Bryce Woodworth, cloud and TurnTrout

13 Jun 2025 13:45 UTC

239 points

43 comments8 min readLW link

(arxiv.org)