AIs like ChatGPT fall apart in classic 'Stroop' psychological test — and that could stand in the way of achieving artificial general intelligence

A robot standing thoughtfully in front of a giant digital display with code on it.

• A new study tasked AIs with tackling the 'Stroop' test
• GPT and Claude performed very poorly compared to humans
• There are nuances here, but broadly, the researchers argue that improving this side of AIs is crucial for achieving artificial general intelligence

A freshly published study has pointed out a limitation of big-name AI models such as ChatGPT, albeit causing some controversy as the primary piece of research uses now outdated versions of those models – but there are nuances therein, and this doesn't make the findings irrelevant.