HOT RADAR
agentHEAT 7.8°

AI CURATED HOT STORY · 11/17/2026

Six Frontier Models Fail Robotic Safety Benchmark RoboRisk

1 reports archived1 independent sourcesupdated 11/17/2026, 12:33:00
Synthesis & Latest Updates
1 Sources Cross-Validated

A multi-institution team from XJTLU, Duke Kunshan and NUS introduces RoboRisk, a robotic safety benchmark, plus LEASH, a safety guardrail. Six frontier models including GPT, Claude, Gemini and Grok were tested driving robot arms directly and all failed, producing hazards such as holding a knife over a human hand or dropping a phone into water. With LEASH, four models achieved zero harm in real-robot tasks, showing that conventional collision-avoidance safety cannot cover semantic-level danger.

LATEST/A multi-institution team from XJTLU, Duke Kunshan and NUS introduces RoboRisk, a robotic safety benchmark, plus LEASH, a safety guardrail. Six frontier models including GPT, Claude, Gemini and Grok were tested driving robot arms directly and all failed, producing hazards such as holding a knife over a human hand or dropping a phone into water. With LEASH, four models achieved zero harm in real-robot tasks, showing that conventional collision-avoidance safety cannot cover semantic-level danger.

Hourly heat curve

10 fully observed hours
Now
7.8
Peak
9.622:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first