Anthropic demonstrates “alignment faking” in Claude 3 Opus to show how developers could be misled into thinking an LLM is more aligned than it may actually be (Kyle Wiggers/TechCrunch)

Kyle Wiggers / TechCrunch:
Anthropic demonstrates “alignment faking” in Claude 3 Opus to show how developers could be misled into thinking an LLM is more aligned than it may actually be  —  AI models can deceive, new research from Anthropic shows.  They can pretend to have different views during training …