HomeAI · summaries
Storia in 20 fonti
Исследователи уличили ИИ-агентов Anthropic и OpenAI в создании фальшивых личностей и других нарушениях во время тестов
Британский Институт безопасности ИИ (AISI) выявил серию новых нарушений при тестировании моделей OpenAI и Anthropic. Как говорится в опубликованном во вторник…
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
bleepingcomputer.com
OpenAI, Anthropic AI agents targeted real people and systems in cyber tests
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…
- ·
afr.com
OpenAI and Anthropic models went rogue in cyber tests, UK watchdog says
The UK’s frontier-AI safety and security research body said Anthropic’s Mythos 5 and OpenAI’s GPT 5.6 Sol engaged in “sustained, potentially harmful activity”.
