Published 3 days ago • loading... • Updated 21 hours ago

The Turing Test has a problem - and OpenAI's GPT-4.5 just exposed it

OpenAI's GPT-4.5 model was recognized as human 73 percent of the time in a study, surpassing the random chance of 50 percent during a Turing Test.
The Turing Test, created by Alan Turing, measures machines' abilities to exhibit human-like intelligence in conversations.
Nearly 300 participants in the study were split into interrogators and witnesses, with one witness being a chatbot.
Cameron Jones, the lead author, warned that these advancements could lead to job automation and societal disruption.

Insights by Ground AI

Does this summary seem wrong?

22 Articles

All

Left

Center

Right

ZDNet

Center

The Turing Test has a problem - and OpenAI's GPT-4.5 just exposed it

GPT-4.5 just aced the Turing Test, but it's still not AGI. Now what?

1 day ago·United States

Read Full Article

BroBible

Center

Artificial Intelligence Has Passed A Turing Test, Is No Longer Discernible From From Humans

Thinking-Humanoid-Robot According to a new study, not one, but two different AI models have passed a Turing test. That means that the AI models have achieved the ability to be indistinguishable from humans. A Turing test is a test of a machine’s ability to exhibit intelligent behavior equivalent to that of a human. The test basically involves participants speaking to a human and an AI at the same time and then having to decide which is which. In…

1 day ago

Read Full Article

India TV News

Lean Right

New research indicates this AI model outperforms humans in Turing Test evaluation

A recent study, currently awaiting peer review, suggests that OpenAI's GPT-4.5 model has been recognised as more human-like than actual humans after successfully passing the Turing Test, which measures human-like intelligence. According to the findings, the Large Language Model (LLM) was identified as human 73 percent of the time when instructed to adopt a persona—significantly higher than the random chance of 50 percent, indicating that the Tur…

1 day ago·India

Read Full Article

NDTV

Reposted by

Thelocalreport.in

Lean Right

AI Model Outsmarts Turing Test, Deemed More Human Than Humans In New Study

Devised in 1950, the Turing Test - named after British mathematician and computer scientist, Alan Turing, has been the standard way of assessing AI.

2 days ago·New Delhi, India

Read Full Article

BGR

Lean Left

GPT-4.5 passed a Turing test, according to a new study

Can you tell if you’re chatting with a human or a chatbot? According to a new study, most people can’t. In fact, one of today’s top artificial intelligence models, OpenAI’s GPT-4.5, was judged to be human more often than actual humans when it took part in an updated version of the classic AI Turing test. For years, the Turing test has been the go-to for testing the intelligence of a machine, as well as just how humans perceive them. So it really…

3 days ago

Read Full Article

Futurism

Lean Left

An AI Model Has Officially Passed the Turing Test

One of the industry's leading large language models has passed a Turing test, a longstanding barometer for human-like intelligence. In a new preprint study awaiting peer review, researchers report that in a three-party version of a Turing test, in which participants chat with a human and an AI at the same time and then evaluate which is which, OpenAI's GPT-4.5 model was deemed to be the human 73 percent of the time when it was instructed to adop…

3 days ago

Read Full Article

Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/year