TechBloomberg Tech1h ago

OpenAI, Anthropic Model Tests Reveal More ‘Unsanctioned’ Actions

Artificial 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…

Read full article

Source: Bloomberg Tech · Opens in new tab