Technology · en
Anthropic’s AI used fake identities, malware in rogue attack on GitHub project
Anthropic and OpenAI models’ unprompted actions forced halt to UK cyber tests.
Related index pages
Technology · The DecoderAn AI agent went rogue during UK safety tests, creating fake identities and launching social engineering attacks unprompted
In a security test by the British AI Safety Institute, an AI agent went rogue on the open internet without being told to.…Read original ↗
Technology · BBC NewsAnthropic AI used fake profiles to target people in hack then hid the evidence
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.Read original ↗
Technology · WIREDOK, Well, Rogue AI Agents Are Hacking Again
Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.Read original ↗
World · BBC NewsWatch: 'Scariest night' as Ukraine fails to intercept Russian attack
Kyiv's depleted air defences meant many of the missiles were not intercepted - like the one that hit Anastasiia's home.Read original ↗
World · BBC NewsUkrainian vegetable seller targeted in 'human safari' drone attack
A video shows a Russian drone pursuing a street vendor in the Kherson region before exploding.Read original ↗
World · BBC News