Pros and cons of ChatGPT plugin, Code Interpreter, in education, biology, health

Science Daily  August 25, 2023 A team of researchers in the US (University of West Virginia, South Dakota University, Arizona State University) have found limitations for its use by scientists who work with biological data utilizing computational methods to prioritize targeted treatment for cancer and genetic disorders. According to them bioinformatics tasks often require execution of third-party packages, access to annotation knowledgebase, and handling large datasets. Code Interpreter’s exclusive support for Python, no installation option for additional packages, inability to utilize external resources, and limited storage capacity could pose obstacles to its wide adoption in bioinformatics applications. To address these […]

Six tips for better coding with ChatGPT

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 […]

Major publishers are banning ChatGPT from being listed as an academic author. What’s the big deal?

Phys.org January 31, 2023 Several papers published recently have listed ChatGPT as an author. Last week, both the Science and Nature journals declared their positions on the use of ChatGPT to generate articles. Science is updating its license and editorial policies to “specify that text generated by ChatGPT (or any other AI tools) cannot be used in the work, nor can figures, images, or graphics be the products of such tools”. Similarly, Nature has formulated the following principles: “No LLM (large language model) tool will be accepted as a credited author on a research paper… Researchers using LLM tools should […]