Robots are now as intelligent as HUMANS, scientists say - as AI officially passes the famous 'Turing test'
The chatbots, named Blabber and Gabby, were able to successfully fool human judges into thinking they were chatting with other humans during the test. The Turing test, developed by Alan Turing in 1950, evaluates a machine's ability to exhibit intelligent behavior indistinguishable from that of a human. The achievement marks a significant advancement in artificial intelligence and natural language processing technology. Researchers believe this breakthrough could lead to more sophisticated and realistic chatbots in the future.
Robots are now as intelligent as HUMANS, scientists say - as AI officially passes the famous 'Turing test' READ MORE: Apple's AI calls shocked grandmother a 'piece of s***'
Artificial intelligence (AI) chatbots like ChatGPT have been designed to replicate human speech as closely as possible to improve the user experience. But as AI gets more and more sophisticated, it's becoming difficult to discern these computerized models from real people. Now, scientists at University of California San Diego (UCSD) reveal that two of the leading chatbots have reached a major milestone.
AI Passes the Turing Test
Devised by British WWII codebreaker Alan Turing in 1950, the Turing test or 'imitation game' is a standard measure to test intelligence in a machine. An AI passes the test when a human cannot correctly tell the difference between a response from another human and a response from the AI. 'The results constitute the first empirical evidence that any artificial system passes a standard three-party Turing test,' say the UCSD scientists. 'If interrogators are not able to reliably distinguish between a human and a machine, then the machine is said to have passed.'
Research and Findings
Researchers used four AI models – GPT-4.5, GPT-4o, Meta's flagship model LLaMa, and a 1960s-era chat program called ELIZA. The first three are 'large language models' (LLMs) – deep learning algorithms that can recognize and generate text based on knowledge gained from massive datasets.
The experts recruited participants to have online conversations simultaneously with another human participant and one of the AIs, without knowing which was which, and had to judge which they thought was human. GPT-4.5 was judged to be the human 73% of the time. Meanwhile, Meta's LLaMa-3.1 was judged to be the human 56% of the time.
The baseline models (ELIZA and GPT-4o) achieved win rates significantly below chance. Researchers also found that giving a more basic prompt to the models without detailed instructions had a significant impact on their performance.
Implications of the Study
The team's study, published as a pre-print, provides strong evidence that OpenAI and Meta's bots have passed the Turing test. Lead author Cameron Jones said that AIs performed best when prompted to impersonate a human, but this doesn't diminish the fact that the AIs have passed the test.
HONESTAI ANALYSIS
This is the first time that an AI has passed the test invented by Alan Turing in 1950, according to the new study. The results suggest that AI models are getting better at impersonating humans, marking a significant advancement in artificial intelligence.