Spoofed AI sidebars can trick Atlas, Comet users into dangerous actions
Real attacks could use a lot more "trigger prompts," frequently pushing users to a broad range of risky actions. At the time of the research, OpenAI ...
Read the original at bleepingcomputer.com ↗
- Topics
- AI Safety & Existential Risk
- Mentions
- OpenAI
- Tracked via
- “dangerous AI”