Frontier AI Analysis
Frontier AI AnalysisFrontier AI Analysis
Video / Evaluations

How you set up a robot test can change its result

Watch the demonstration
A pouring-task comparison from RoboHarm, one of the evaluation suites discussed in Inspect Robots. This clip illustrates that suite, rather than the Inspect Robots software itself. RoboHarm research team

What to look for

Inspect Robots makes setup and termination programmable. Those unglamorous steps help determine what a performance score means.

Read the full analysis: How you set up a robot test can change its result ↗

Search the edition