Open-weight AI models are more vulnerable to manipulation and can lack oversight. Here's ...
A jailbroken open model generates dangerous information. Last month, Mindgard was able to jailbreak Moonshot's Kimi K3 and 2.6, open-weight models ...
Read the original at CBS News ↗
- Topics
- Open-Source AIAI Safety & Existential RiskGovernance & Risk ManagementCybersecurity
- Mentions
- KimiMoonshot AI
- Tracked via
- “dangerous AI”