Large language models’ ability to generate text also lets them plan and reason

Quantum physicsLLMLLM as a Shakespearean sonnet. Trade theory explained by a pirate. A children’s story about a space-faring dinosaur. People have had fun asking modern chatbots to produce all sorts of unusual text. Some requests have been useful in the real world—think travel itineraries, school essays or computer code. Modern large language models (s) can generate them all, though homework-shirkers should beware: the models may get some facts wrong, and are prone to flights of fancy that their creators call “hallucinations”.Occasional hiccups aside, all this represents tremendous progress. Even a few years ago, such programs would have been science fiction. But churning out writing on demand may not prove to be s’ most significant ability. Their text-generating prowess allows them to act as general-purpose reasoning engines. They can follow instructions, generate plans, and issue commands for other systems to carry out.