Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Paper • 2609.29429 • Published • 10
mara ilie
Marailie
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 17 hours ago
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures upvoted a paper about 17 hours ago
MatrAIx: Simulating the World with 8.3 Billion Persona Agents liked a model 5 days ago
surogate/rune-26b-a4b-GGUFOrganizations
upvoted 2
papers about 17 hours ago
