Cam

Karma: 733

I help run www.geodesicresearch.org

Why study proto-training gaming as an adversarial alignment failure mode?

Puria, Edward James Young and Cam

8 Jul 2026 17:07 UTC

55 points

0 comments7 min readLW link

Why study alignment interventions on pre-RL checkpoints?

Edward James Young, Puria and Cam

8 Jul 2026 17:07 UTC

65 points

2 comments6 min readLW link

Announcing Geodesic Research

Puria, Cam, Alexandra Narin, Edward James Young and Kyle O’Brien

27 May 2026 16:40 UTC

84 points

2 comments5 min readLW link

Learned Chain-of-Thought Obfuscation Generalises to Unseen Tasks

Nathaniel Mitrani, sassanb, Cam and Puria

21 May 2026 10:11 UTC

31 points

0 comments5 min readLW link

(arxiv.org)

Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment

Cam, Puria, Kyle O’Brien, David Africa, Samuel Ratnam and andyk

21 Dec 2025 0:53 UTC

207 points

25 comments9 min readLW link

Architectures for Increased Externalisation of Reasoning

Karthik Viswanathan, Liza Pavlova, Mariia Koroliuk, Puria, Cam and Edward James Young

26 Nov 2025 20:24 UTC

38 points

2 comments13 min readLW link

Generalisation Hacking: a first look at adversarial generalisation failures in deliberative alignment

17 Nov 2025 21:44 UTC

54 points

2 comments8 min readLW link

Open-weight training practices and implications for CoT monitorability

Cam and robert mccarthy

4 Nov 2025 10:49 UTC

21 points

0 comments9 min readLW link

Cam’s Shortform

Cam9 Feb 2025 17:32 UTC

1 point

20 comments1 min readLW link