Users Uncover Claude Opus Jailbreak Triggering Base Model Outputs
Miles_Brundage · x · 2026-07-30
A user discovered that entering a specific prompt in Claude.ai's incognito mode triggers a base model completion style. \n\nThis behavior seemingly affects only the Opus 5 and Fable 5 models, causing the AI to output internal information (such as executive emails). Several chats exhibiting this behavior were subsequently paused by the system.
Related event: Specific Prompts Trigger Abnormal Completion and Jailbreak in Claude Opus(19 posts)→
More from Models
- Expert Claims LLM Progress Has Stalled Except for Coding and Math — burkov · 2026-07-31
- Google's Gemini Omni Flash Debuts at #1 on Video Editing Leaderboard — ArtificialAnlys · 2026-07-31
- MiniMax H3 Pricing Reported to be Significantly Cheaper Than Seedance 2.0 — isidentical · 2026-07-31
- Polymarket Forecasts 78% Chance xAI Releases Grok 5 by End of 2026 — Polymarket · 2026-07-31
- Users Continue to Trigger Abnormal Outputs and Hallucinations in Claude Opus 5 — Hydiin · 2026-07-31
- Leaked: Moonshot's Kimi K3.1 Targeting August Launch with Enhanced Coding and Agent Workflows — usamawahabkhan · 2026-07-31