A fundamental flaw leaves LLMs strikingly vulnerable to attack

MIT Technology Review reports that it is impossible to make large language models fully secure against hacks because of a fundamental flaw in how they work, a team of researchers argue in a paper presented at the International Conference on Machine Learning, a top…

For Australian readers, the useful question is what this changes in everyday work: costs, productivity, privacy, hiring, or the tools businesses rely on. We are watching this story because practical AI adoption is moving quickly, and the impact often reaches workplaces before policy or training catches up.