The NY Times: “A.I. Is Getting More Powerful, But Its Hallucinations are Getting Worse”

From The NY Times:

More than two years after the arrival of ChatGPT, tech companies, office workers and everyday consumers are using A.I. bots for an increasingly wide array of tasks. But there is still no way of ensuring that these systems produce accurate information.

The newest and most powerful technologies — so-called reasoning systems from companies like OpenAI, Google and the Chinese start-up DeepSeek — are generating more errors, not fewer. As their math skills have notably improved, their handle on facts has gotten shakier. It is not entirely clear why.

{Clip]

For more than two years, companies like OpenAI and Google steadily improved their A.I. systems and reduced the frequency of these errors. But with the use of new reasoning systems, errors are rising. The latest OpenAI systems hallucinate at a higher rate than the company’s previous system, according to the company’s own tests.

The company found that o3 — its most powerful system — hallucinated 33 percent of the time when running its PersonQA benchmark test, which involves answering questions about public figures. That is more than twice the hallucination rate of OpenAI’s previous reasoning system, called o1. The new o4-mini hallucinated at an even higher rate: 48 percent.

[Clip]

“The way these systems are trained, they will start focusing on one task — and start forgetting about others,” said Laura Perez-Beltrachini, a researcher at the University of Edinburgh who is among a team closely examining the hallucination problem.

Learn More, Read the Complete Article (about 1300 words)

Filed under: News