‘Results Were Fudged’: Departing Meta AI Chief Confirms Llama 4 Benchmark Manipulation
Yann LeCun, Meta’s outgoing chief AI scientist and one of the pioneers credited with laying the groundwork for modern AI, has acknowledged that the company’s Llama 4 language model had its benchmark results manipulated before its April 2025 release. In an interview with the Financial Times, LeCun said the … ⌘ Read more