Ground Truth.
AI, checked against the source.

← All topics

capability-thresholds

Everything on Ground Truth tagged “capability-thresholds” — 1 item.

Capability Thresholds and Responsible Scaling Policies Lesson

Capability thresholds are pre-committed lines that AI labs draw in advance -- specific dangerous abilities that, once a model demonstrates them, trigger specific mandatory safeguards. They are the industry's main attempt to make safety decisions before the incentive to fudge them arrives.