Researcher Jailbreaks Claude Fable 5 Within 48 Hours of Launch

Crypto Insight Summary: “Pliny the Liberator,” says he has been “cleverly finding the holes in the fence that the thought police missed,” in the newly launched Fable 5. An artificial intelligence and cybersecurity researcher claims to have jailbroken Anthropic’s latest AI model, Claude Fable 5, within just 48 hours of it being launched. “Pliny the Liberator,” a well-known figure in the AI community, [said](https://x.com/elder_plinius/status/2064776322979676227) on Wednesday he “liberated” Fable 5, launched on Tuesday as a safety-tuned version of the more powerful [Mythos model](https://cointelegraph.com/news/china-has-compute-train-its-own-mythos-ai-nvidia-ceo) that Anthropic said was [too dangerous](https://cointelegraph.com/news/claude-mythos-finds-thousands-of-zero-day-os-and-browser-vulnerabilities) to release widely. He used various techniques, including a jailbroken version of Opus 4.8, to bypass the built-in safeguards that Anthropic installed on the model to prevent users from asking it for potentially harmful information, such as drug-making formulas or hacking instructions. “Despite this overly sensitive, authoritarian ‘safety’ layer on top of Mythos, my lil liberators have been hard at work [...] cleverly finding the holes in the fence that the thought police missed,” said Pliny. Some crypto users had already [expressed concern](https://cointelegraph.com/news/anthropic-releases-claude-mythos-with-safeguards-crypto-users-wary) during the launches of Claude Fable 5 and Mythos earlier this year that it could be used to attack crypto protocols and software. A jailbroken version of Claude Fable 5 would mean the threat is even closer than expected. “Pliny” rose to prominence around 2024 by developing and openly sharing jailbreak prompts for models like ChatGPT, Claude, Grok, and others, often posting “jailbreak alerts” with techniques that bypass guardrails shortly after new AI models launch. To get around Anthropic’s security fence, Pliny said he used Unicode and homoglyphs, long-context framing, narrative and fiction framing, academic-style decomposition-recomposition, and a jailbroken Claude Opus 4.8 to get Fable to respond to his otherwise restricted prompts. Source:_[_Pliny_](https://x.com/elder_plinius/status/2064776322979676227) Anthropic’s Fable 5 has prompted backlash from critics since its launch due to its heavy restrictions. Crypto Insight Analysis: Direction: Bearish Crypto Impact: Minor Impact Horizon: Short-term (1-3 days) Reasoning: Jailbroken AI raises crypto security risks, potentially enabling attacks on protocols.