Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Paper • 2609.29429 • Published • 23
Thiago Gonzaga PRO
devops-thiago
·
AI & ML interests
open weight models, fine tuning
Recent Activity
upvoted a paper about 14 hours ago
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures liked a model about 14 hours ago
deepseek-ai/DeepSeek-V4.1-Flash liked a model about 14 hours ago
google/gemma-4-E2B-itOrganizations
None yet
upvoted a paper about 14 hours ago