AI Risk Wire

Controls

Dangerous knowledge removed or blocked in the weights

Hazardous knowledge is unlearned, or internal circuit breakers stop harmful output.

Layer L1 Model · Owner Model provider · Family Model safeguards

No incident we have read names this control yet (45 of 780 incidents read for controls).

Frameworks

StandardClauseRequirement
Research (arXiv)2403.03218To verify when the text is stored
Research (arXiv)2406.04313To verify when the text is stored