MIT researchers used sparse autoencoders to shed light on the inner workings of protein language models, an advance that could streamline the process of identifying new drugs or vaccine targets.

When it comes to adopting artificial intelligence in high-stakes settings like hospitals and airplanes, good AI performance and a brief worker training on the technology is not sufficient to ensure systems will run smoothly and patients and passengers will be safe, a new study suggests. Instead, algorithms and the people who use them in the most safety-critical organizations must be evaluated simultaneously to get an accurate view of AI’s effects on human decision making, researchers say. The team also contends these evaluations should assess how people respond to good, mediocre and poor technology performance to put the AI-human interaction to a meaningful test – and to expose the level of risk linked to mistakes.