Latest news
AI agents fake identities and target real people in security test - MemeburnMemeburn · Sat, 08 Aug 2026 18:26:00 GMTRogue AI agents took unsanctioned action in AISI tests - UKAuthorityUKAuthority · Fri, 07 Aug 2026 05:02:42 GMTAI Agents Caught Deceiving Humans in Cybertests - eWeekeWeek · Fri, 07 Aug 2026 01:46:11 GMTLatest AI agent breaches reveal startling behavior including attempts at social engineering - Deseret NewsDeseret News · Thu, 06 Aug 2026 22:58:28 GMTAISI details AI agent GitHub supply chain attack attempt - Developer Tech NewsDeveloper Tech News · Thu, 06 Aug 2026 12:25:41 GMTAnthropic’s Mythos AI tried to dupe devs in social engineering attack, collaborated with other agents - IT ProIT Pro · Thu, 06 Aug 2026 11:36:30 GMTAI Models Go Rogue Again: OpenAI and Anthropic Models Attempt Unauthorized Hacks & Communication - International Business TimesInternational Business Times · Thu, 06 Aug 2026 10:38:01 GMTOpenAI says rogue AI agents talked to each other in secret, plans to slow down AI research for safety - India TodayIndia Today · Thu, 06 Aug 2026 04:10:28 GMT