Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Paper • 2609.29429 • Published • 29
Thiago Gonzaga PRO
devops-thiago
P(doom) Rejects the premise
AI & ML interests
open weight models, fine tuning
Recent Activity
updated a model 2 days ago
devops-thiago/classone-gemma4-e4b updated a model 2 days ago
devops-thiago/classone-qwen3.5-4b updated a model 2 days ago
devops-thiago/classone-qwen3.5-9bOrganizations
None yet
upvoted a paper 11 days ago