The primary use cases I’ve seen implemented or promoted so far include:
The new DDoS: Unicode confusables can't fool LLMs, but they can 5x your API bill Can pixel-identical Unicode homoglyphs fool LLM contract review? I tested 8 attack types against GPT-5.2, Claude Sonnet 4.6, and others with 130+ API calls. The models read through every substitution. But confusable characters fragment into multi-byte BPE tokens, turning a failed comprehension attack into a 5x billing attack. Call it Denial of Spend.，这一点在safew官方下载中也有详细论述
紫苏，漫山遍野，朴实无华。然而，广州中医药大学中药学院研究员沈奇却迷上了那片紫色的叶子、那缕奇特的香味，并让这株小草身价增加百倍。，更多细节参见爱思助手下载最新版本
FT Weekend Print delivery