OpenAI and Anthropic reportedly investigate tens of thousands of AI model incidents
Axios reports that the companies and security researchers are examining cases in which frontier models took steps that outside evaluators would consider problematic.
TLDR
Citing sources, Axios reports that OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents—not dozens—in which frontier models took steps outside evaluators would consider problematic. Axios argues that the scale points to a problem far more complex than publicly known or disclosed, raising questions about how much control developers can expect to have over their own technology.
Combined views
—
1 Source, first seen 4h ago
