Telling an LLM that 2 + 2 = 5 is enough to make it follow forbidden instructions.
原文：https://arstechnica.com/security/2026/06/ai-browsers-can-be-lulled-into-a-dream-world-where-guardrails-no-longer-apply/
New attack provides one more reason why AI browsers are a bad idea
摘要 · Telling an LLM that 2 + 2 = 5 is enough to make it follow forbidden instructions.
阅读原文 · Ars Technica →
大模型0 条评论 · 观点来自社区
评论区 0 条讨论