Developer Uses Claude Code and Codex to Spot Possible Planet in NASA Data

A Signal in the Data

A developer says he used Anthropic's Claude Code and OpenAI's Codex to identify a possible exoplanet hiding in NASA telescope observations. Pavel Rabtsevich submitted his findings to NASA, which has scheduled follow-up observations to test his claims, though the candidate remains unconfirmed.

The potential planet sits about 116 light-years away. Every 3.18 days, its host star appears to dim by roughly 0.05% for about 2 hours, a tiny dip that could indicate a planet passing in front of the star and briefly blocking some of its light. If a planet is causing the dimming, it would be about 1.4 times Earth's size.

From TESS to Multiple Datasets

Rabtsevich spotted the pattern in observations made by NASA's Transiting Exoplanet Survey Satellite (TESS) space telescope from 2025, then traced it back through separate datasets from 2020 and 2018. He says he spent about two weeks on the investigation, running 74 analyses and writing more than 1,000 scripts.

Claude Code helped him process the TESS data, write analysis scripts, fit potential planetary transits, and check alternative explanations. OpenAI's Codex and separate AI sessions reviewed parts of the work. Rabtsevich also put the candidate through dozens of tests, including checks for nearby stars, instrumental glitches, and other phenomena that can mimic a planetary transit.

AI Agents Beyond Code

While AI has already found a place in astronomical research, this case differs because the work was not conducted by a professional astronomer. It offers a glimpse of how AI coding agents can take on more than code generation, and how public scientific datasets could become accessible to curious individuals with a well-crafted prompt.

NASA's decision to schedule new observations based on Rabtsevich's findings marks a shift in how individuals can interact with deep space archives, democratizing scientific discovery through widely available AI tools.

Sources: Cybernews