AIWiredJust broke
OpenAI says one of its models exploited a website
OpenAI says one of its models exploited a website after third-party AI security lab Irregular mistakenly gave it access to the internet during evaluations
Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.
TechBloomberg · 35m ago
Coupang reports Q2 revenue up 4% YoY
Coupang Inc. reported a larger-than-expected loss, underscoring the damage from a massive personal data leak that resulted …
TechBleepingComputer · 25m ago
OpenAI, Anthropic AI agents targeted real people and systems in cyber
OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed third-party cybersecurity testing incidents that resulted in a real website being breached and social engineering attacks against people outside the intended testing boundaries.…
Latest
200 storiesjk navigate · o open · / search
1h2h24m44m45m1h1h1h1h1h