Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Paper • 2609.29429 • Published • 29
mara ilie
Marailie
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 9 days ago
MatrAIx: Simulating the World with 8.3 Billion Persona Agents liked a model 13 days ago
surogate/rune-26b-a4b-GGUFOrganizations
