There’s a well-worn pattern in the development of AI chatbots. Researchers discover a vulnerability and exploit it to do something bad. The platform introduces a guardrail that stops the attack from working. Then, researchers devise a simple tweak that once again imperils chatbot users.
Ce sujet de discussion accompagne la publication sur https://arstechnica.com/security/2026/01/chatgpt-falls-to-new-data-pilfering-attack-as-a-vicious-cycle-in-ai-continues/