RSS

ChengCheng

Karma: 128

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

Feb 7, 2025, 3:57 AM
29 points
0 comments10 min readLW link

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

Nov 1, 2024, 12:10 AM
18 points
0 comments6 min readLW link
(far.ai)

Pac­ing Out­side the Box: RNNs Learn to Plan in Sokoban

Jul 25, 2024, 10:00 PM
59 points
8 comments2 min readLW link
(arxiv.org)

Does ro­bust­ness im­prove with scale?

Jul 25, 2024, 8:55 PM
14 points
0 comments1 min readLW link
(far.ai)

VLM-RM: Spec­i­fy­ing Re­wards with Nat­u­ral Language

Oct 23, 2023, 2:11 PM
20 points
2 comments5 min readLW link
(far.ai)

Un­cov­er­ing La­tent Hu­man Wel­lbe­ing in LLM Embeddings

Sep 14, 2023, 1:40 AM
32 points
7 comments8 min readLW link
(far.ai)