‘Got any men’s sport?’: Triple M radio host who compared Matildas to ‘year 10 girls’ condemned
Lionel Messi cracker lifts Miami over Sporting KC into Champions Cup last-16
‘We try to put applicants off’: couple chosen as live-in caretakers on uninhabited Irish island
Albanese riffs on Trump phone call, Keating’s sledging and ‘gotcha’ journalism on Grade Cricketer podcast spin-off
Officer stripped of security clearance over Israel loyalty still in Australian defence force
Researchers at UCLA found GPT-3 solved 80% of reasoning problems correctly compared with 60% of humans
ChatGPT can solve problems at a level that matches or surpasses an undergraduate student, according to a new study.
Researchers found that the GPT-3 large language model that underpins the chatbot performed better than US college undergraduates when asked to solve reasoning problems that appear on intelligence tests or exams such as the American college admission test, the SAT.
More Stories
I became absorbed in strangers’ fertility journeys online
Microsoft unveils chip it says could bring quantum computing within years
Virologist Wendy Barclay: ‘Wild avian viruses are mixing up their genetics all the time. It’s like viral sex on steroids’