Each time a brand new AI mannequin is launched, it’s sometimes touted as acing its efficiency towards a collection of benchmarks. OpenAI’s GPT-4o, for instance, was launched in Could with a compilation of outcomes that confirmed its efficiency topping each different AI firm’s newest mannequin in a number of exams.
The issue is that these benchmarks are poorly designed, the outcomes onerous to copy, and the metrics they use are steadily arbitrary, in accordance with new analysis. That issues as a result of AI fashions’ scores towards these benchmarks decide the extent of scrutiny they obtain.
AI firms steadily cite benchmarks as testomony to a brand new mannequin’s success, and people benchmarks already kind a part of some governments’ plans for regulating AI. However proper now, they may not be adequate to make use of that approach—and researchers have some concepts for a way they need to be improved.
—Scott J Mulligan
We have to begin wrestling with the ethics of AI brokers
Generative AI fashions have turn into remarkably good at conversing with us, and creating pictures, movies, and music for us, however they’re not all that good at doing issues for us.
AI brokers promise to vary that. Final week researchers revealed a brand new paper explaining how they skilled simulation brokers to copy 1,000 individuals’s personalities with beautiful accuracy.
AI fashions that mimic you could possibly exit and act in your behalf within the close to future. If such instruments turn into low cost and straightforward to construct, it’ll elevate a lot of new moral considerations, however two specifically stand out. Learn the total story.
—James O’Donnell
