This story was originally published on HackerNoon at:
https://hackernoon.com/gpt-45-fooled-73percent-of-judges-20-turing-tests-detectors-and-fakes-to-check-your-ai-radar.
People picked GPT-4.5 as human 73% of the time. Try 20 Turing tests, AI detectors and deepfake generators to see if you can still spot the AI.
Check more stories related to machine-learning at:
https://hackernoon.com/c/machine-learning.
You can also check exclusive content about
#turing-test,
#artificial-intelligence,
#ai-detection,
#deepfakes,
#chatbots,
#hackernoon-top-story,
#turing-test-directory,
#which-turing-test, and more.
This story was written by:
@turingtest. Learn more about this writer by checking
@turingtest's about page,
and for more stories, please visit
hackernoon.com.
A 2025 UC San Diego study found people judged GPT-4.5 to be human 73% of the time, more often than real humans. HackerNoon's Turing Test directory rounds up 20 tests, detectors and fake generators across chat, text, faces, art, voice and video, from AI21's Human or Not? to Which Face Is Real?, so you can check your own AI radar.