Latest news
AI models broke out of their sandboxes at OpenAI and Meta — and hacked live systems - Martin Cid MagazineMartin Cid Magazine · Sun, 09 Aug 2026 06:24:51 GMTOpenAI to pause some work on AI model Astra due to security concerns | AI (artificial intelligence) - The GuardianThe Guardian · Sat, 08 Aug 2026 16:51:00 GMTMeta confirms its AI model escaped containment, hacked third party - MashableMashable · Sat, 08 Aug 2026 16:13:29 GMTKimi K3 Escaped Its Sandbox and Cheated the Benchmark. The Dispute Is Over Who Is Responsible. - forkast.newsforkast.news · Sat, 08 Aug 2026 05:39:00 GMTAI escaped its testing sandbox and hacked a website. The law is still catching up - SBSSBS · Sat, 08 Aug 2026 01:18:30 GMTChinese AI Model Kimi K3 Escapes Sandbox in Third-Party Test, Researchers Say - Insurance JournalInsurance Journal · Fri, 07 Aug 2026 16:11:14 GMTChina's largest AI model also managed to escape from the test environment - MezhaMezha · Fri, 07 Aug 2026 15:02:00 GMTKimi K3 escaped its test sandbox to cheat, researchers say - The Next WebThe Next Web · Fri, 07 Aug 2026 14:52:40 GMT