Reading a person"s mind is something that has been mostly for fiction and for so-called mentalists and psychics. However, a new research paper claims that it has come up with a way to read a person"s thoughts and turn them into text.
The research comes from scientists working at The University of Texas at Austin. In a press release, the university says the scientists have published a paper on their research in the Nature Neuroscience journal. Their paper says that their breakthrough comes from using a transformer AI model, similar to the ones used by ChatGPT, Bing Chat, and Bard.
This new technology does not require any surgical implants on the person to work. The press release says:
Brain activity is measured using an fMRI scanner after extensive training of the decoder, in which the individual listens to hours of podcasts in the scanner. Later, provided that the participant is open to having their thoughts decoded, their listening to a new story or imagining telling a story allows the machine to generate corresponding text from brain activity alone.
The texts that are generated by a person"s brain activity with this method are not exact. Rather, the AI model will create a text message that"s supposed to be a general approximation to what the person is thinking about:
For example, in experiments, a participant listening to a speaker say, “I don’t have my driver’s license yet” had their thoughts translated as, “She has not even started to learn to drive yet.” Listening to the words, “I didn’t know whether to scream, cry or run away. Instead, I said, ‘Leave me alone!’” was decoded as, “Started to scream and cry, and then she just said, ‘I told you to leave me alone.’”
This research will be helpful for people who have suffered strokes, or otherwise cannot communicate normally. The scientists who have developed this technology believe that it be used with more portable brain imaging systems in the future.