Post #4374500

Researchers say a fundamental flaw in LLMs makes it easy to trick them into doing things they shouldn’t — like telling you how to sabotage an aircraft’s navigation system. "There’s a real probability that this is going to be a problem that’s fundamentally unsolvable," says one of the paper's coauthors. https://www.technologyreview.com/2026/07/30/1140927/a-fundamental-flaw-leaves-llms-vulnerable-to-attack/ #AI #LLMs #AIResearch #GenerativeAI #security