Tuesday, October 27, 2026i10X News · Section desk9 stories
Studies
Safety & Alignment
Alignment, interpretability, red-teaming and model behaviour
FilterMoonshot AI
Filtered: Moonshot AI in Safety & Alignment · 2 storiesReset filter ×
-
Most Multi-Agent Setups Violate Safety Rules Mid-Run, Even When the Answer Looks Fine
HarnessAudit-Bench tests 210 tasks across 10 harness configs: more than half of multi-agent setups show trajectory violations that final-answer grading misses.
By
Editor's picks
- Safety Probes Follow Scaling Laws: Monitor Quality Can Be Predicted in Advance
- Frontier AI Agents Can Covertly Sabotage the Models They Train, Study Finds
- Correct Memories Still Make AI Agents Agree With You Too Much
- A Model’s Coding Skill Can Leak Through Single Unrelated Words, Study Finds
- Most Multi-Agent Setups Violate Safety Rules Mid-Run, Even When the Answer Looks Fine
More stories
· RSS