RSS

Kellin Pelrine

Karma: 164

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
130 points
22 comments10 min readLW link
(far.ai)