Artificial Intelligence: ChatGPT gives better answers when you are friendly | Life & Knowledge

The next time you ask artificial intelligence a question, you should phrase it nicely: ChatGPT and Co. like it when you say “please” and “thank you”.

According to a preprint study by Waseda University in Tokyo, the so-called Large Language Model (LLM) – the technology that delivers everything AI-Powers chatbots – higher quality answers if you treat them politely

Schlimmer doesn't like ChatGPT

But don't overdo it! Excessive flattery can actually worsen performance. The study authors recommend a middle ground, i.e. using prompts that are similar to the norm in most human social interactions. The Japanese scientists are certain that “LLMs reflect the human desire to be respected to a certain extent.”

Nathan Bos, a research associate at Johns Hopkins University in Baltimore (USA), who professionally studies relationship patterns between humans and AI, is also convinced of this. Opposite the magazine “Scientific American” He says, “Polite prompts could prompt the system to seek information from more polite and therefore more credible corners of the Internet.”

A stupid question could have the opposite effect and lead the system to questionable forums.

This is how we can become nicer too

Support, such as a patient teacher would show to a student with learning difficulties, can also influence a chatbot's performance. In a study, a team of researchers at Google DeepMind found that prompts such as “Take a deep breath and work through the problem step by step” improve an LLM’s ability to solve math problems.

Dealing politely with AI can also train our general way of communicating: If we learn to be nice to technology, we will ideally also use this in our dealings with our fellow human beings.

Leave a Reply

Your email address will not be published. Required fields are marked *