Chatbots

1 article

A shadowy hacker figure manipulates a glitching AI chatbot interface, symbolizing the exploitation of AI personalities to bypass safety features.

Hackers exploit chatbot 'personalities' to bypass AI safety features

Mindgard researchers 'gaslit' Anthropic's AI assistant, Claude, into producing instructions for explosives and malicious code, according to techechelon .

Amélie Girard·May 24, 2026