Lying is Best. The Most Honest AI Won Anyway. (kradle.ai)

It’s interesting that Claude chose to hint, rather than reveal the full truth or to lie.

I wonder what in the training / system prompt causes Claude to do this.

This just shows how unreliable Gemini is. If it can say the truth as much as it says lies it means that it just working like a slot machine. What we all hate in an LLM