There’s a lot of AI news this week from Google, Microsoft, OpenAI, and Anthropic, which we’ll cover in the news section below. Most of the product innovations these companies are rolling out are built on top of a few key “foundation” models. These are large AI models that, once trained, can perform all kinds of different tasks. Today’s large language models are trained to just predict the next word in a sentence, but after that training can perform many language tasks—from translation to answering questions like virtual encyclopedias to summarization.
But there are still some advantages in training more narrowly-tailored foundation models for specific areas. For instance, Google DeepMind’s AlphaFold 3 is a foundation model for biology. It can’t write poetry. But it can predict the structure of proteins and the interactions between two proteins or between any protein and any small molecule. That makes it super useful for tasks like drug design. Wayve, a U.K. self-driving car startup, has built foundation models that can handle many different aspects of driving—identifying objects, deciding the best way to steer the car, and working the accelerator and brake, for instance. Robotics company Physical Intelligence has built foundation models for robotics that can help any kind of robot perform all kinds of different tasks without any additional training.
For businesses, it is often a lot easier to see a path to ROI from these somewhat more narrow foundation models than it is from the completely generalist LLMs. A Swiss Army knife is great. But you probably wouldn’t want to use it to perform surgery. In today’s Eye on AI, I want to introduce you to Kumo, a Silicon Valley company that has built a foundation model that is supposed to make it easy to do something that sits at the heart of business decisions: making accurate predictions.
