🖥️ **Cryptographers Show That AI Protections Will Always Have Holes**

"_Large language models such as ChatGPT come with filters to keep certain info from getting out. A new mathematical argument shows that systems like this can never be completely safe._"

🔗 https://www.quantamagazine.org/cryptographers-show-that-ai-protections-will-always-have-holes-20251210/.

#AI #ArtificialIntelligence #Technology #Tech #ComputerScience #LLMS #MachineLearning