{"type":"analysis","id":"analysis:research-one-reused-safety-research-prompt-broke-most-of-23-models-but-layered","slug":"research-one-reused-safety-research-prompt-broke-most-of-23-models-but-layered","title":"One reused safety-research prompt broke most of 23 models, but layered safeguards held at Anthropic and Meta","description":"A MATS researcher turned a synthetic-transcript generator into a jailbreak template. It reached 84–100% attack success on nine models from 7 providers. Separate FAR.AI testing found a similar gap: hundreds of universal jailbreaks on Gemini 3.1 Pro and Grok 4.5, and none on Claude Fable 5 or GPT-5.6 Sol.","published_at":"2026-10-23T15:00:00.000Z","updated_at":"2026-10-23T15:00:00.000Z","record_date":"2026-10-23","topics":["gemini","claude","anthropic","research"],"source_urls":["https://lesswrong.com/posts/hHk5CpiqZTBBiHmYt/from-safety-research-prompt-to-cross-model-universal","https://far.ai/news/clearharm-a-more-challenging-jailbreak-dataset","https://www.far.ai/blog/ai-security-leaderboard","https://arxiv.org/abs/2608.03070","https://ai-frontiers.org/articles/ai-jailbreak-disclosure-is-broken-heres-how-to-fix-it"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-one-reused-safety-research-prompt-broke-most-of-23-models-but-layered/","markdown":"https://newruntime.com/analysis/research-one-reused-safety-research-prompt-broke-most-of-23-models-but-layered.md","json":"https://newruntime.com/analysis/research-one-reused-safety-research-prompt-broke-most-of-23-models-but-layered.json"},"author":{"role":"author","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"editorial_provenance":{"desk":"authorial","target_ref":"deep_research:da6a33bd-539a-449c-843a-dcfcf5bf07f8","authorial_article_id":"da6a33bd-539a-449c-843a-dcfcf5bf07f8"},"next_reads":[{"type":"topic","path":"/topics/gemini/","url":"https://newruntime.com/topics/gemini/","title":"Gemini","reason":"Explore the gemini topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/gemini.md","json_url":"https://newruntime.com/topics/gemini.json"},{"type":"topic","path":"/topics/claude/","url":"https://newruntime.com/topics/claude/","title":"Claude","reason":"Explore the claude topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude.md","json_url":"https://newruntime.com/topics/claude.json"},{"type":"topic","path":"/topics/anthropic/","url":"https://newruntime.com/topics/anthropic/","title":"Anthropic","reason":"Explore the anthropic topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/anthropic.md","json_url":"https://newruntime.com/topics/anthropic.json"},{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}