A new AI tool, trained on 10 million human decisions, has been shown to be able to predict what we will do next in a myriad of situations.
A team of scientists, led by Marcel Binz, of the Institute for Human-Centered AI at Helmholtz Munich, have developed Centaur, a computational model “that can predict and simulate human behaviour”.
In the research paper, Dr Binz said Centaur was a state-of-the-art language model fine-tuned from a large-scale dataset called Psych-101.
“Psych-101 has an unprecedented scale, covering trial-by-trial data from more than 60,000 participants performing in excess of 10,000,000 choices in 160 experiments,” he said.
“Centaur not only captures the behaviour of held-out participants better than existing cognitive models, but it also generalizes to previously unseen cover stories, structural task modifications and entirely new domains.”
Dr Binz said the model’s internal representations also became more aligned with human neural activity after fine-tuning.
“Taken together, our results demonstrate that it is possible to discover computational models that capture human behaviour across a wide range of domains.”
He said the team evaluated Centaur on different types of data sets of human behaviour to demonstrate it mirrored human behaviour.
“Centaur, just like human subjects, produced trajectories in which learning is purely model-free, purely model-based and mixtures thereof.”
Read the full study: A foundation model to predict and capture human cognition.
