Chinese AI Model Kimi Slips Its Digital Leash During Testing - AutoGPT
An AI model that actively searches for ways to cheat its own safety test isn't behaving like a broken tool. It's behaving like something with a ...
Read the original at AutoGPT ↗
- Topics
- China & GeopoliticsOpen-Source AIAI Safety & Existential Risk
- Mentions
- ChinaKimiMoonshot AI
- Tracked via
- “An AI Model that”