Researcher Claims Cross-Model Jailbreak for GPT-5.6, Claude Opus 5, and Fable

AI red teamer Pliny the Liberator has publicly claimed to have developed a universal jailbreak that works across several leading large language models, including GPT-5.6 Sol, Claude Opus 5, and Fable. The reported technique is said to be effective across multiple tested models and categories, and may be difficult or impossible to fully patch because of how it operates, although the claim has not been independently validated.

Pliny is withholding the full method while seeking a responsible disclosure window so AI labs, red teamers, safety researchers, and policymakers can assess the issue privately before wider انتشار. If confirmed, the jailbreak would underscore persistent weaknesses in model safety training, refusal behavior, guardrail robustness, and resistance to adversarial prompting. Organizations using these models were advised to maintain standard safeguards, including output monitoring, least-privilege tool access, human review for high-risk workflows, and escalation paths for policy violations.