Researchers gave top artificial intellect models a classic attention test used in psychology and found a major flaw. Some leading systems fell from over 90% accuracy to nearly complete failure. While the models could correctly name colors in short lists, their performance deteriorated sharply as the task became longer and more complex.
Related Posts
VentureBeat names Rob Strechay as its first Lead Analyst, expanding its enterprise AI research push
He later served as a senior analyst at Enterprise Strategy Group and most recently as managing director and principal analyst…
Alan Turing's biggest AI assumption may have been wrong
He believes this makes true human-level artificial intellect impossible, regardless of how large language models become. A new book claims…
Algorithms don’t care: how AI worsens the double burden for Indonesia’s female gig workers
artificial intelligence-driven platforms pull informal labour into the global digital economy but push the risks and responsibilities back onto workers.…