How to vibe code in science: early adopters share their tips

"Last year, climate researcher Zeke Hausfather was playing around with climate-data visualizations, trying to find new and shocking ways to show just how fast Earth is warming. He was brainstorming ideas with an artificial-intelligence tool and getting it to code and create them quickly. Together, they made innovative tree-ring-style plots with the months of the year around each ring, the annual circles growing outwards with time and the colours showing temperature."

"Then Hausfather asked the AI tool: what if these plots were 3D? The result was what Hausfather calls a thermal helix animation, showing temperature spiralling upwards through time into a shape reminiscent of a tornado (see 'A new view'). In a world in which most people have seen the classic 'hockey-stick' graph of rising global temperatures, it is a refreshing graphic: compelling and beautiful."

"Thanks to large language models (LLMs), people can now simply ask their computers to write and implement code for graphics, applications, data processing and just about anything else they can imagine. This kind of laid-back, conversational technique is often called vibe coding. Andrej Karpathy, co-founder of US firm OpenAI, coined the term last year."

"It refers to asking an LLM-powered tool to build or do something with code behind it, with the user providing clarifying prompts until the results look right. At its purest, vibe coding doesn't involve looking at the code - just the product. But the term has no strict definition, so what counts as vibe coding is fuzzy."

A climate researcher used an AI tool to rapidly create novel temperature visualizations based on tree-ring-style plots. The researcher then asked for a 3D version, producing a thermal helix animation where temperature spirals upward through time into a tornado-like shape. The resulting graphic is presented as compelling and visually refreshing compared with the familiar hockey-stick temperature chart. The work is framed within the broader use of large language models that can write and implement code for graphics, applications, and data processing. This approach is commonly called vibe coding, where users iteratively prompt an AI tool until the output looks right, sometimes without inspecting the underlying code.

Read at Nature