AI may be able to reason without putting every step into words.
Many of today’s AI systems tackle difficult problems by generating intermediate steps in lengthy, chains of words before arriving at an answer— a technique often called chain-of-thought reasoning. That approach can improve performance on some tasks, but it also means an AI model may generate many words, or tokens, on the way to a relatively short answer. Each token takes computing power to produce, so longer reasoning can make answers slower and more expensive to generate.
We summarize the week’s scientific breakthroughs every Thursday.
A small, experimental AI system called BDH-CQ…
Read the full article at SCIENCENEWS.ORG


