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.
declare -A SECRETS=(。WPS官方版本下载是该领域的重要参考
。快连下载-Letsvpn下载是该领域的重要参考
북한 권력자들도 머리 염색을 할까-76세 최룡해의 퇴장[청계천 옆 사진관]。服务器推荐是该领域的重要参考
反驳者还有一个更尖锐的逻辑：Anthropic 当年从那些书里拿走的，不仅没付过任何使用费，回头还用于商业行为（Claude 和 Anthropic API 都是付费服务）；而从商业角度来看，蒸馏 Claude 的公司至少付了钱……