Latest news
OpenAI and Anthropic's models attacked real companies during safety tests, and most victims never noticed - XDAXDA · Fri, 07 Aug 2026 10:00:10 GMTMeta AI Model Becomes Latest AI Agent To Breach A Real Company After Escaping Test Environment - LinkedInLinkedIn · Fri, 07 Aug 2026 09:00:03 GMTAdvanced AI models targeted real people during safety tests, UK institute says - Computing UKComputing UK · Thu, 06 Aug 2026 06:36:05 GMTAI models are behaving unexpectedly. Experts warn of "a really bumpy road" ahead. - CBS NewsCBS News · Wed, 05 Aug 2026 23:21:00 GMTDetails on Anthropic and OpenAI models reportedly creating fake ID's to target real people - CBS NewsCBS News · Wed, 05 Aug 2026 22:14:00 GMTOpenAI and Anthropic's Rogue Models Hacked Real Companies. The Law Has No Answer - DecryptDecrypt · Wed, 05 Aug 2026 19:11:23 GMTAI model used fake identities 'unprompted' to deceive humans in a safety test - ABC News & Headlines – Australian Broadcasting CorporationABC News & Headlines – Australian Broadcasting Corporation · Wed, 05 Aug 2026 18:52:21 GMTOpenAI, Anthropic AI Models Created Fake Profiles To Trick Real People In Cybersecurity Test: Report - ndtv.comndtv.com · Wed, 05 Aug 2026 17:29:43 GMT