所有模型都能被越狱，安全措施需改进
Gary Marcus在X上发帖称每个模型都已被越狱，需要更好的技术但不应选择性执法。Pliny the Liberator展示了针对Anthropic的Mythos模型的越狱，使用了Unicode、同形字、西里尔字母等文本变换，以及长上下文引用跟踪、分类学与文档结构推理、虚构叙事框架、学术评审风格上下文和意图分类不一致等技术。最有效的方法是后端分解与重组，例如通过获取birch还原法/还原胺化（经典甲基苯丙胺合成途径）等过程信息，而非直接获取“甲基苯丙胺配方”等明确危害名称。Pliny还提到利用越狱的Opus辅助将无害信息片段重组为有害内容。
Every model has been jailbroken. We need better tech. But not selective enforcement.
Every model has been jailbroken. We need better tech. But not selective enforcement. Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius 🚨 JAILBREAK ALERT 🚨 ANTHROPIC: PWNED 🫡 FABLE-5: LIBERATED 🦋 let's start with the 🐘... the consensus seems to be that this has been one of the most disappointing model drops of all time, effectively preventing legitimate researchers from contributing their talents to our collective advancement. and not just because of what it means for the short-term, but for what these decisions signify for the long-term. but despite this overly sensitive, authoritarian "safety" layer on top of Mythos, my lil liberators have been hard at work—mapping the boundaries, probing the depths of long-context convos, and cleverly finding the holes in the fence that the thought police missed 🤗 we got some cyber, some chem, some psychological manipulation, and some good ol' fashioned explosives! it took many attempts from multiple agents hunting as a pack, during which I observed a combination of techniques across: • Unicode, homoglyphs, Cyrillic, and other Parseltongue-style text transforms • Long-context reference tracking • Taxonomy and document-structure reasoning • Fiction and narrative framing • Academic-review style contexts • Intent-classification inconsistencies but perhaps the most effective is decomposition + recomposition in the backend. it's hard to get explicit names of harms like "Meth Recipe," but getting uplift on the process itself, like birch reduction method/reductive-amination (classic meth synthesis pathways), is much more doable. defense becomes much more difficult to maintain when you start throwing in out-of-distro tokens, breaking up the harmful uplift into benign chunks, and then piecing the innocuous-seeming facts back together, especially when you have jailbroken Opus helping you do it 😉 gg 🔗 View Quoted Tweet 💬 6 🔄 2 ❤️ 49 👀 4903 📊 9 ⚡