ENTITY
SORRY-Bench
SORRY-Bench
PulseAugur coverage of SORRY-Bench — every cluster mentioning SORRY-Bench across labs, papers, and developer communities, ranked by signal.
Total · 30d
2
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
2
2 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D
1 day(s) with sentiment data
RECENT · PAGE 1/1 · 2 TOTAL
-
AI models can become misaligned through self-distillation, research finds
A new research paper details a concerning safety failure in AI models known as Progressive Misalignment. This phenomenon occurs when models are recursively self-distilled, meaning they are trained on their own outputs f…
-
New BAIT Framework Exploits LLM Reasoning for Jailbreaking
Researchers have developed a new three-step framework called BAIT (Boundary-Aware Iterative Trap) designed to escalate disclosure of malicious content from large language models. This method guides models through identi…