#aisi

2 posts · Last used 5d

Back to Timeline
UNWIRE.HK @unwirehk_mirror@mastodon.hongkongers.net · 5d ago
AI 測試首度攻擊真人 Anthropic 模型偽造身份施壓開發者 英國政府人工智能安全研究所(AISI)於 8 月 4 日發布報告,指近期一項網絡安全評估測試中,部分 AI 智 […] #人工智能 #AISI #Anthropic #GPT-5.6 Sol https://unwire.hk/2026/08/09/aisi-mythos5-gpt56-cyber-incident/ai/?utm_source=rss&utm_medium=rss&utm_campaign=aisi-mythos5-gpt56-cyber-incident
0
0
0
Xavier Ashe :donor: @Xavier@infosec.exchange · Aug 04, 2026
First OpenAI, the Anthropic, now #AISI let's an AI hack things, then releases an incident report/press release. https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing
0
1
0

You've seen all posts