ZZürich Read More “With AI, we often confuse behaviour with intention”2026-09-30 Recent safety tests have shown advanced AI systems making misleading statements, concealing information, or attempting to prevent their…
ZZürich Read More The researcher making AI safer2026-05-25 Even as a teenager, Javier Rando was fascinated by technology, computers and the idea that robots could one day take…
ZZürich Read More ETH Zurich researchers discover new security vulnerability in Intel processors2026-04-03 Breaking through the built-in protective barriers between users, known as privileges, is possible because the permissions for individual…