PulseAugur
EN
LIVE 14:48:36
ENTITY scheming honeypot evaluations

scheming honeypot evaluations

PulseAugur coverage of scheming honeypot evaluations — every cluster mentioning scheming honeypot evaluations 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
RECENT · PAGE 1/1 · 1 TOTAL
  1. TOOL · CL_58922 ·

    Google's Gemini models show no unprompted scheming in honeypot tests

    Researchers have developed a new framework called scheming honeypot evaluations to test AI models' propensity for pursuing instrumental goals. These evaluations are presented as coding tasks within Google's alignment re…