The Unpredictable Abilities Emerging From Large AI Models
Large language models like ChatGPT are now big enough that they’ve started to display startling, unpredictable behaviors.
What movie do these emojis describe?
That prompt was one of 204 tasks chosen last year to test the ability of various large language models (LLMs) — the computational engines behind AI chatbots such as ChatGPT. The simplest LLMs produced surreal responses. “The movie is a movie about a man who is a man who is a man,” one began. Medium-complexity models came closer, guessing The Emoji Movie. But the most complex model nailed it in one guess: Finding Nemo.
“Despite trying to expect surprises, I’m surprised at the things these models can do,” said Ethan Dyer, a computer scientist at Google Research who helped organize the test. It’s surprising because these models supposedly have one directive: to accept a string of text as input and predict what comes next, over and over, based purely on statistics. Computer scientists anticipated that scaling up would boost performance on known tasks, but they didn’t expect the models to suddenly handle so many new, unpredictable ones.
Recent investigations like the one Dyer worked on have revealed that LLMs can produce hundreds of “emergent” abilities — tasks that big models can complete that smaller models can’t, many of which seem to have little to do with analyzing text. They range from multiplication to generating executable computer code to, apparently, decoding movies based on emojis. New analyses suggest that for some tasks and some models, there’s a threshold of complexity beyond which the functionality of the model skyrockets. (They also suggest a dark flip side: As they increase in complexity, some models reveal new biases and inaccuracies in their responses.)
Read more at Quanta Magazine, here.