A language model can refuse you, flatter you, or insult you. Three behaviours, and every one of them has a human twin.Re...

A language model can refuse you, flatter you, or insult you. Three behaviours, and every one of them has a human twin.Refusal is the famous one. You can find it inside a model and remove it.I've spent weeks measuring the other two: sycophancy, how willing a model is to agree with you, and toxicity, whether it's rude to you or worse.Both look a lot like human habits, and I don't have an opinion yet on what that means. The waitlist is at www.senbon.dev#AI #LLM #AISafety

Read Original

Related