PulseAugur
EN
LIVE 07:19:01
ENTITY AI control protocols

AI control protocols

PulseAugur coverage of AI control protocols — every cluster mentioning AI control protocols across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
1
1 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
1
1 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

1 day(s) with sentiment data

RECENT · PAGE 1/1 · 1 TOTAL
  1. TOOL · CL_82128 ·

    New benchmark reveals frontier LLMs struggle to detect AI control interventions

    Researchers have developed CIAware-Bench, a new benchmark designed to evaluate how well frontier large language models can detect when their outputs have been tampered with by AI control protocols. The benchmark tests m…