A look at the BabyLM Challenge, which aims to create language models with datasets that are less than one-ten-thousandth the size of those used by advanced LLMs (Oliver Whang/New York Times)

Oliver Whang / New York Times:
A look at the BabyLM Challenge, which aims to create language models with datasets that are less than one-ten-thousandth the size of those used by advanced LLMs  —  Teaching fewer words to large language models might help them sound more human.  —  When it comes to artificial intelligence chatbots, bigger is typically better.