OpenAI GPT 4.5 Pass Turing Test
UC San Diego researchers announced this week that OpenAI’s GPT 4.5 has officially passed the Turing Test. The researchers conducted a three-party Turing Test where people talked with both a human and an AI for five minutes, then judged which was which.



When GPT-4.5 was instructed to adopt a human-like persona—specifically, an introverted, geeky 19-year-old, it was identified as human 73% of the time. For comparison, older models like ELIZA scored around 22%, and even GPT-4o hovered below 50%. This means that GPT-4.5 didn’t just parrot responses; it adapted to context, injected personality, and kept 73% of testers guessing wrong.

Meta Quest 3S 128GB — Get Batman: Arkham Shadow and a 3-Month Trial of Meta Quest+ Included —...

Meta Quest 3S 128GB — Get Batman: Arkham Shadow and a 3-Month Trial of Meta Quest+ Included —…

  • Transform your reality and do everything you love in totally new ways. Welcome to Meta Quest 3S. Now you can get the Batman: Arkham Shadow* and a…
  • Explore thousands of unreal experiences with mixed reality, where you can blend digital objects into the room around you or dial up the immersion in…
  • Have more fun with friends in Quest. Whether you’re stepping into an immersive game with people from around the world, watching a live concert…

This has sparked buzz about what’s next for AI. Some say the Turing Test, dreamed up by Alan Turing in 1950, might be losing its edge as a benchmark since modern language models are getting so good at imitation. If AI can pass as human in casual chats, it would leave the door open for more seamless integration into daily life. In other words, people might start treating AI as companions, not just tools, whether it be customer service, mental health support, or even creative collaboration.
[Source]