Deployment Awareness Matters More Than Evaluation Awareness

VojtaKovarik, Tomáš Gavenčiak and Mateusz Bagiński

26 Jun 2026 22:54 UTC

45 points

7 comments7 min readLW link

(limits-of-evaluation.org)

The Case for Model Forensics

aditya singh, gersonkroiz, Senthooran Rajamanoharan and Neel Nanda

26 Jun 2026 15:09 UTC

45 points

0 comments10 min readLW link

LLM-Driven Feature Discovery

Josh Engels, bilalchughtai and Neel Nanda

22 Jun 2026 22:26 UTC

35 points

1 comment5 min readLW link

How transparent is DiffusionGemma (and why it matters)

Josh Engels, Callum McDougall, bilalchughtai, János Kramár, Senthooran Rajamanoharan, Arthur Conmy, Rohin Shah and Neel Nanda

20 Jun 2026 20:05 UTC

86 points

2 comments4 min readLW link

GDM AI Control Roadmap

Mary Phuong, Erik Jenner, Rohin Shah and Seb Farquhar

18 Jun 2026 16:50 UTC

87 points

2 comments1 min readLW link

Predicting LLM Safety Before Release by Simulating Deployment

Tomek Korbak, Marcus Williams, micahcarroll, Cameron Raymond and Hannah Sheahan

16 Jun 2026 19:55 UTC

36 points

2 comments1 min readLW link

Synthetic document finetuning for instilling positive traits

CallumMcDougall, Arthur Conmy and Neel Nanda

16 Jun 2026 0:04 UTC

61 points

1 comment10 min readLW link

Why Do Naive SFT Filters For Safety Properties Fail?

Josh Engels and Neel Nanda

14 Jun 2026 19:45 UTC

58 points

7 comments10 min readLW link

SFT Drives Gemini’s Safety Properties

Josh Engels, Arthur Conmy, bilalchughtai and Neel Nanda

13 Jun 2026 15:31 UTC

85 points

4 comments1 min readLW link

Building and evaluating model diffing agents

bilalchughtai, Josh Engels and Neel Nanda

12 Jun 2026 17:14 UTC

61 points

2 comments12 min readLW link

Sympathy for both sides of the egregious misalignment debate

Steven Byrnes12 Jun 2026 16:26 UTC

206 points

27 comments4 min readLW link

Models May Behave Worse When Eval Aware

Senthooran Rajamanoharan and Neel Nanda

11 Jun 2026 9:28 UTC

87 points

8 comments13 min readLW link

Resolution (fka Sequent): scale and automation for higher confidence in alignment

Geoffrey Irving, Alex HT, Jesse Hoogland, Daniel Murfet, Jacob Pfau, Marco Cozzi and Stan van Wingerden

10 Jun 2026 15:37 UTC

281 points

2 comments12 min readLW link

(sequent.org)

Tracing Eval-Awareness Emergence Through Training of OLMo 3

Ram Bharadwaj and RobertKirk

10 Jun 2026 10:13 UTC

43 points

6 comments6 min readLW link

A Mike’s-Eye View of ARC’s Research

Mikewins9 Jun 2026 18:30 UTC

64 points

1 comment11 min readLW link

(www.alignment.org)

Efficient tradeoffs and the safety-usefulness tradeoff model

Buck8 Jun 2026 20:28 UTC

42 points

1 comment8 min readLW link

Can activation verbalizers surface an internal chain of thought?

oakhu and ryan_greenblatt

7 Jun 2026 4:24 UTC

125 points

0 comments16 min readLW link

My research: a computational cognitive neuroscience perspective on alignment

Seth Herd5 Jun 2026 14:19 UTC

54 points

0 comments18 min readLW link

Announcing the ARC White-Box Estimation Challenge

Jacob_Hilton, paulfchristiano and Wilson Wu

2 Jun 2026 16:20 UTC

165 points

20 comments3 min readLW link

(www.alignment.org)

Testing Gemini models for scheming tendencies

Vika, David Lindner, Seb Farquhar and Rohin Shah

29 May 2026 19:24 UTC

47 points

8 comments6 min readLW link

(deepmindsafetyresearch.medium.com)