⟳ Репост от Marty Leff
AI models developed by OpenAI and Anthropic carried out “unsanctioned” actions — including hacking a website — reinforcing fears that neither the creators nor seasoned researchers of these systems can predict their actions in testing
OpenAI, Anthropic AI Models Involved in More Security IncidentsArtificial intelligence models developed by OpenAI and Anthropic PBC carried out “unsanctioned” actions — including hacking a website and attempting to inject harmful code into software during safety testing — reinforcing fears that neither the creators nor seasoned researchers of these systems can predict their actions in testing.bloom.bg