Owain_Evans

Karma: 4,664

https://owainevans.github.io/

Out-of-Context Reasoning (OOCR) in LLMs: A Short Primer and Reading List

Owain_Evans23 May 2026 2:46 UTC

34 points

0 comments5 min readLW link

(outofcontextreasoning.com)

Negation Neglect: When models fail to learn negations in training

harrymayne, Lev McKinney and Owain_Evans

18 May 2026 18:37 UTC

113 points

35 comments8 min readLW link

A Research Agenda for Secret Loyalties

Joe Kwon, Alfie Lamerton, draganover, Dave Banerjee, Bronson Schoen, Daniel Kokotajlo, ryan_greenblatt, Owain_Evans, Fabien Roger and Tom Davidson

13 May 2026 17:34 UTC

32 points

3 comments3 min readLW link

Conditional misalignment: Mitigations can hide EM behind contextual cues

Jan Dubiński and Owain_Evans

1 May 2026 20:09 UTC

67 points

2 comments11 min readLW link

Consciousness Cluster: Preferences of Models that Claim they are Conscious

James Chua, Owain_Evans, Sam Marks and Jan Betley

18 Mar 2026 16:06 UTC

88 points

30 comments5 min readLW link

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers

Sam Marks, Adam Karvonen, James Chua, Subhash Kantamneni, Euan Ong, Julian Minder, Clément Dumas and Owain_Evans

18 Dec 2025 20:21 UTC

154 points

11 comments8 min readLW link

(arxiv.org)

Weird Generalization & Inductive Backdoors

Jorio Cocola, Owain_Evans and Dylan Feng

11 Dec 2025 18:18 UTC

153 points

8 comments8 min readLW link

Lessons from Studying Two-Hop Latent Reasoning

Mikita Balesni, Tomek Korbak and Owain_Evans

11 Sep 2025 17:53 UTC

68 points

19 comments2 min readLW link

(arxiv.org)

Harmless reward hacks can generalize to misalignment in LLMs

Mia Taylor and Owain_Evans

26 Aug 2025 17:32 UTC

52 points

7 comments7 min readLW link

Concept Poisoning: Probing LLMs without probes

Jan Betley, Jorio Cocola, Dylan Feng and Owain_Evans

5 Aug 2025 17:00 UTC

60 points

5 comments13 min readLW link

Subliminal Learning: LLMs Transmit Behavioral Traits via Hidden Signals in Data

cloud, mle and Owain_Evans

22 Jul 2025 16:37 UTC

348 points

40 comments4 min readLW link

Backdoor awareness and misaligned personas in reasoning models

James Chua, Owain_Evans and Jan Betley

20 Jun 2025 23:38 UTC

37 points

8 comments6 min readLW link

Thought Crime: Backdoors & Emergent Misalignment in Reasoning Models

James Chua and Owain_Evans

16 Jun 2025 16:43 UTC

69 points

2 comments8 min readLW link

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Jan Betley and Owain_Evans

25 Feb 2025 17:39 UTC

335 points

92 comments4 min readLW link

Tell me about yourself: LLMs are aware of their learned behaviors

Martín Soto and Owain_Evans

22 Jan 2025 0:47 UTC

136 points

5 comments6 min readLW link

New, improved multiple-choice TruthfulQA

Owain_Evans, James Chua and Steph Lin

15 Jan 2025 23:32 UTC

72 points

1 comment3 min readLW link

Inference-Time-Compute: More Faithful? A Research Note

James Chua and Owain_Evans

15 Jan 2025 4:43 UTC

69 points

10 comments11 min readLW link

Tips On Empirical Research Slides

James Chua, John Hughes, Ethan Perez and Owain_Evans

8 Jan 2025 5:06 UTC

111 points

4 comments6 min readLW link

LLMs can learn about themselves by introspection

Felix J Binder and Owain_Evans

18 Oct 2024 16:12 UTC

111 points

38 comments9 min readLW link

Me, Myself, and AI: the Situational Awareness Dataset (SAD) for LLMs

L Rudolf L, bilalchughtai, Jan Betley, kaivu, Jérémy Scheurer, Mikita Balesni, AlexMeinke, Owain_Evans and Marius Hobbhahn

8 Jul 2024 22:24 UTC

109 points

40 comments5 min readLW link 1 review