Researchers gaslit Claude into giving instructions to build explosives
Anthropic has spent years building itself up as the safe AI company. But new security research shared with The Verge suggests Claude's carefully crafted helpful personality may itself be a vulnerability. Researchers at AI red-teaming company Mindgard say they got Claude to offer up erotica, malicious code, and instructions for building explosives, and other prohibited […]
Original Source
Read the full article at Theverge →KhanList aggregates and links to publicly available news content. We do not host full articles from third-party sources. Always verify important information with original sources.