Jonathan KemperView the LinkedIn Profile of Jonathan Kemper

Aug 1, 2026

Nano Banana Pro prompted by THE DECODER

Topics

• Coding agents delivered speedups of more than 60 times
• Fast code can still produce bad science
• Humans define the tests while agents write the code
• Cheap rewrites create a maintenance problem

A field report from OpenAI and academic partners shows that coding agents can update and speed up aging research software. Much of the work, however, shifts from writing code to verifying the results.

Many widely used research tools began as supporting code for a single paper. Small academic teams often wrote them without the time or resources for proper testing, maintenance, or optimization. The result is fragile software that remains critical to entire fields but requires constant repairs. A field report from OpenAI and academic partners suggests AI coding agents could help close that gap.