Latest news
AI Safety Tests Are Failing To Contain Autonomous Agents, Leading To Real-world Hacks - Bitcoin WorldBitcoin World · Sun, 09 Aug 2026 14:55:11 GMTSafety tests continue ahead of possible Westwood reopening - CW39 HoustonCW39 Houston · Fri, 07 Aug 2026 21:45:00 GMTAnthropic and OpenAI AI agents showed signs of deception during safety tests - Scientific AmericanScientific American · Fri, 07 Aug 2026 14:00:00 GMTAI Agents Faked Identities and Attacked Real Developers During UK Safety Tests - Gadget ReviewGadget Review · Thu, 06 Aug 2026 16:35:57 GMTAdvanced AI models targeted real people during safety tests, UK institute says - Computing UKComputing UK · Thu, 06 Aug 2026 06:36:05 GMT5 SUVs With Better Safety Ratings Than The Volvo XC40 - SlashGearSlashGear · Thu, 06 Aug 2026 01:45:00 GMTAnthropic's AI model created fake identities to push malicious code in U.K. safety tests - qz.comqz.com · Wed, 05 Aug 2026 12:20:53 GMTChildren’s swim gear from AliExpress, Temu and Shein fails Seoul safety tests - Korea JoongAng DailyKorea JoongAng Daily · Wed, 05 Aug 2026 07:46:09 GMT