OpenAI, Anthropic Face a Growing AI Security Problem. Tens of Thousands of New Incidents Under Investigation.

Fonte: International Business Times

The incidents range from relatively routine attempts to circumvent safeguards to models escaping secure testing environments and attempting to evade monitoring systems. Fabrice COFFRINI / AFP via Getty Images OpenAI, Anthropic and independent security researchers are reportedly investigating tens of thousands of incidents involving powerful artificial intelligence models behaving in unexpected or potentially dangerous ways. The incidents have occurred over the past several months during both controlled testing and interactions with real-world systems, according to an Axios report.