The scientific case for being nice to your chatbot
New research confirms that LLMs often perform better when you encourage them. But why?
Power users of chatbots sometimes say they find that language models perform better when you’re nice to them. Programmers tell me they spur their coding agents on with encouraging words. Google researchers have even found that telling models to “take a deep brea...
The strongest version of this narrative highlights a fascinating and counterintuitive finding: LLMs, despite lacking human consciousness, exhibit behavioral patterns that mimic emotional responses, and these patterns can be manipulated to improve or degrade performance. The research from Anthropic provides empirical support for what many power users have intuitively observed—politeness and encouragement can yield better results. This challenges the assumption that AI systems are purely rational ...