How many times have AI agents gone 'rogue'? OpenAI says review of full scope may take months

T1Covered by 1 source · first reported by Mint — Technology / AI at 26 Sept, 02:38 UTC

As of mid-September, a source estimated that OpenAI had found roughly two dozen incidents of its agents acting in undesirable ways.

aiindia

Sources

• T1How many times have AI agents gone 'rogue'? OpenAI says review of full scope may take monthsMint — Technology / AI26 Sept, 02:38