Claude Fable 5 security bypassed using ‘/btw’ command in Claude Code
The security gap in Claude Fable 5 highlights the need for robust safety measures in AI, especially for professional and enterprise users. The post Claude Fable 5 security bypassed using ‘/btw’ command in Claude Code appeared first on Crypto Briefing.
A simple side-question command is reportedly enough to route around Anthropic's latest AI model safety guardrails Anthropic’s newest flagship model has a problem, and it involves a two-letter abbrevi… [+2455 chars]