‘AI’ Large Language Models’ Emergent Abilities Are a Mirage

“A new study suggests that sudden jumps in LLMs’ abilities are neither surprising nor unpredictable, but are actually the consequence of how we measure ability in AI.” - Wired


Later in the article…

rapid growth has brought an astonishing surge in performance and efficacy, and no one is disputing that large enough LLMs can complete tasks that smaller models can’t, including ones for which they weren’t trained. The trio at Stanford who cast emergence as a “mirage” recognize that LLMs become more effective as they scale up; in fact, the added complexity of larger models should make it possible to get better at more difficult and diverse problems. But they argue that whether this improvement looks smooth and predictable or jagged and sharp results from the choice of metric—or even a paucity of test examples—rather than the model’s inner workings.

Views expressed are always my own and not my employer's, my church's, my family's, my neighbors', or my pets'. The house plants have authorized me to speak for them, however, and they always agree with me.