Kellin Pelrine

Karma: 173

Persuasion Undermining Control: Can AI Talk its Way Out of Human Control?

Josh Levy, myang_ and Kellin Pelrine

18 Sep 2026 16:34 UTC

10 points

0 comments7 min readLW link

(www.far.ai)

Investigating Accidental Misalignment: Causal Effects of Fine-Tuning Data on Model Vulnerability

Zhijing Jin, Punya Syon Pandey, samuelsimko and Kellin Pelrine

11 Jun 2025 19:30 UTC

6 points

0 comments5 min readLW link

Illusory Safety: Redteaming DeepSeek R1 and the Strongest Fine-Tunable Models of OpenAI, Anthropic, and Google

ChengCheng, Brendan Murphy, Adrià Garriga-alonso, Yashvardhan Sharma, dsbowen, smallsilo, Yawen Duan, ChrisCundy, Hannah Betts, AdamGleave and Kellin Pelrine

7 Feb 2025 3:57 UTC

37 points

0 comments10 min readLW link

GPT-4o Guardrails Gone: Data Poisoning & Jailbreak-Tuning

ChengCheng, Brendan Murphy, AdamGleave and Kellin Pelrine

1 Nov 2024 0:10 UTC

18 points

0 comments6 min readLW link

(far.ai)

Even Superhuman Go AIs Have Surprising Failure Modes

AdamGleave, EuanMcLean, Tony Wang, Kellin Pelrine, Tom Tseng, Yawen Duan, Joseph Miller and MichaelDennis

20 Jul 2023 17:31 UTC

131 points

22 comments10 min readLW link

(far.ai)