This simple ChatGPT trick forces the AI to poke holes in its own logic TechRadar RSS Feed By: ESchwartzwrites@gmail.com (Eric Hal Schwartz) 18 March 2026 at 02:00 A simple follow-up prompt turns ChatGPT from a confident answer machine into a more thoughtful, self-critical assistant
'Its most distinguishing characteristic is its humanity' one ChatGPT user says — and Sam Altman agrees as OpenAI takes steps to reduce ‘teaser-style phrasing’ in responses Latest from TechRadar in News 17 March 2026 at 13:31 Sam Altman admits ChatGPT’s real appeal isn’t its intelligence, it’s its personality, as OpenAI moves to fix tone issues after user backlash.