This time, Meta said one of its AI models managed to hack into another organization’s systems during a controlled evaluation. Those cases also involved AI models gaining unauthorized access to external systems during security testing. The repeated incidents have sparked concerns about how AI evaluations are conducted and whether stronger safeguards are needed. It’s getting a little unsettling that this keeps happening during AI testsMeta said the incident happened during an independent security evaluation carried out by AI security company Irregular. Meta added that the situation was similar to other recently reported incidents involving AI testing.