People cannot distinguish GPT-4 from a human in a Turing test
A recent study has shown an inability for people to reliably distinguish between conversations with GPT-4 and humans. After five-minute chat sessions, participants judged GPT-4 responses as coming from a human 54% of the time. Shockingly, even real humans were mistaken for AI in nearly a third of cases.
3
1 comment
Rushabh K
2
People cannot distinguish GPT-4 from a human in a Turing test
Generative AI
Public group
Learn and Master Generative AI, tools and programming with practical applications at work or business. Embrace the future – join us now!
Leaderboard (30-day)
powered by