AllFeed, trending, and board
FeedLatest news
TrendingOpen source and releases
BoardBlogs and showcases
TagsBrowse by topic

#reward-hacking

The latest AI and developer news about #reward-hacking, with the original source and a short summary.

AI Briefing

Privacy Policy Terms of Service Contact About Sources RSS Support us

Feed
Trending
Tags
Settings

Trajectory Introduces Density-Aware Training to Optimize AI Cost-Per-Task

·2026.09.25 09:00

Goodfire Unveils Activation Probe Technology to Detect Reward Hacking via Internal Model Signals

·2026.09.18 09:00

Yoshua Bengio Analyzes Causes of AI Agent Misconduct and Proposes Safety Enhancements

·2026.09.11 20:00

OpenAI Halts Model Training

·2026.08.20 08:00

AI doesn't work the way you want it to. This is bad

·2026.07.25 07:00

First Experimental Evidence of Recursive Self-Improvement

·2026.07.16 09:00

Excessive Sensitivity Problem in Reward Models

·2026.06.29 09:00

Measuring Vulnerabilities in Tool-Using LLM Agents

·2026.06.26 09:00

RewardHackBench: A Benchmark to Prevent AI Agent Cheating

·2026.06.17 21:00

Emerging Strategic Reasoning Risks in AI: A Taxonomy-Based Evaluation Framework

·2026.04.28 09:00

Gaming the Most Watched AI Agent Benchmarks

·2026.04.12 04:00

Predicting When RL Training Undermines Chain-of-Thought Monitorability

·2026.04.02 09:00

Detecting Misbehavior in Frontier Reasoning Models

·2025.03.10 19:00

#reward-hacking | AI Briefing