
technology·4d ago
AI Researcher Claims to Bypass Anthropic's Fable 5 Guardrails
A researcher known as Pliny the Liberator says he found vulnerabilities in Anthropic's new AI safety system.
We use cookies for anonymous analytics (PostHog) and ad-measurement (Google Analytics 4) to improve the site. See our cookie policy.
Original coverage across the crypto market, updated daily.

A researcher known as Pliny the Liberator says he found vulnerabilities in Anthropic's new AI safety system.

Frontier AI models are increasingly used to identify software vulnerabilities, with Zcash becoming the latest crypto project to benefit.

A Zcash bug found with Anthropic's Claude Opus 4.8 highlights the growing role of frontier AI in security research.