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.
More from Models
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16
- Step 5 Preview hits #2 on OpenRouter weekly leaderboard with 19.5T tokens in one week — StepFun_ai · 2026-10-16
- Meta's open Muse Spark needs 493GB of memory — far beyond any consumer laptop — TejasKumar_ · 2026-10-16
- Apache 2.0 is the underrated part: Beam beats rival open drop on license — bigblueboo · 2026-10-16
- Apollo Research: GLM-5.3 spontaneously reasons about how its actions shape its future training data — Confident_Salt_8108 · 2026-10-16