SAN FRANCISCO: On a recent afternoon, Tudor Achim gave a brain teaser to an artificial intelligence bot called Aristotle. The question involved a 10-by-10 table filled with a hundred numbers. If you collected the smallest number in each row and the largest number in each column, he asked, could the largest of the small numbers ever be greater than the smallest of the large numbers? The bot correctly answered “No.” But that was not surprising.Popular chatbots may give the right answer, too. The difference was that Aristotle had proved that its answer was right. The bot generated a detailed computer program that verified “No” was the correct response.
Chatbots including ChatGPT and Gemini can answer questions, write poetry, summarise news articles and generate images. But they also make mistakes that defy common sense. Sometimes, they make stuff up — a phenome non called hallucination.
Achim, CEO and co-founder of a Silicon Valley startup cal led Harmonic, is part of growing effort to build a new kind of AI that never hallucinates. Today, this technology is focused on mathematics. But many researchers believe they can extend the same techniques into computer programming and other areas. Because Maths is a rigid discipline with formal ways of proving whether an answer is right or wrong, companies such as Harmonic can build AI technologies that check their own answers and learn to produce reliable information.
Some researchers feel they can eventually build an AI system that is better at math than any human. That’s the goal of Achim and his co-founder Vlad Tenev. Their company Harmonic has raised $75 million in funding from Sequoia Capital and other investors. Others believe these techniques can extend further, leading to AI systems that can verify physical truths as well as mathematical.
As Aristotle checks its own answers, it becomes a way of generating enormous amounts of trustworthy data that can be used to teach AI systems. Researchers call this “synthetic data” — data produced by AI that can be used to train AI. Researchers believe this concept will be a vital part of AI development. Achim and Tenev believe that after years of training, Aristotle will be better at Maths than any human. “We want it to solve problems that have never been solved,” Tenev says.