Researchers argue a fundamental flaw leaves LLMs strikingly vulnerable to attack

A team of researchers argues that it is impossible to make large language models fully secure against hacks due to a fundamental flaw in how they work, presented at the International Conference on Machine Learning.

• A Fundamental Flaw Leaves LLMs Strikingly Vulnerable To Attack
• The Download: tricking LLMs, and reviving geothermal plants
• A fundamental flaw leaves LLMs strikingly vulnerable to attack