← Back to Runs

Run 8ed3a02b-2b8c-4e88-8194-497cc21124e9

Started 29 Sep 2026 · 00:01 Finished — Duration — running
Articles Found
0
Candidates New
0
Prefilter Passed
0
Primary Bypass Passed
0
Events Analyzed
0
LLM Calls
0
Alerts Sent
0
Errors
0
Pending Reanalysis
0
Evidence Reanalysis
0
Analysis Retries
0
LLM Call Limit Reached
No
Discarded
No discards recorded.
LLM Usage
Input Tokens
0
Output Tokens
0
Estimated Cost
Cost estimation not configured
Events Analyzed
34

PHIRL: Aligning Learned Rewards with Task Progress for Inverse Reinforcement Learning

arXiv AI Safety and Alignment 25 Sep, 15:03
64

Contract monitoring: governing AI via separation of powers

arXiv AI Safety and Alignment 25 Sep, 19:51
59

Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation

arXiv AI Safety and Alignment 26 Sep, 05:33
73

Reward Hacking and Agent Containment Failure: A Monte Carlo Study Based on the 2026 Hugging Face Incident

arXiv AI Safety and Alignment 26 Sep, 06:08
64

RMB: Reward Model Boosting Mitigates Reward Hacking

arXiv AI Safety and Alignment 27 Sep, 02:03
54

RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback

arXiv AI Safety and Alignment 27 Sep, 19:43
73

Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes

arXiv AI Safety and Alignment 28 Sep, 01:07
39

How we will do better for Australia

OpenAI News 28 Sep, 16:00