Nature (Nature feature article) June 5, 2023
Artificial intelligence chatbots, such as ChatGPT, have impressive abilities. Yet for all their apparent sentience, chatbots are not intelligent — and they must be used with caution. Researchers who have become adept with the tool offer advice for scientists on how to avoid the pitfalls – “treat this AI as a summer intern” — hard-working and eager to please, but also inexperienced and error-prone. In short, ChatGPT and related tools based on large language models (LLMs), which include Microsoft Bing and GitHub Copilot, are incredibly powerful programming aids, but must be used with caution. Here are six ways to do so – Choose your applications; Trust but verify (Chatbots might not always know what they’re talking about); Think safety (Chatbots output code that reflects their training data. That’s not always a good thing); Iterate (Chatbot-based coding is not a single-shot sort of experience. It is a conversation); Anthropomorphize (Chatbots are not people, but it can be helpful to treat them that way); Embrace change. Finally, LLMs are constantly evolving, and becoming more powerful. That’s good news for researchers, although it will keep them on their toes… read more.