Skip to content
Trending storyDeveloping

Anthropic researcher uses Claude Science to build first complete UV sky map

2 articles2 sourcesLast article 7h ago

Overview

AI overview

Johns Hopkins astrophysicist Brice Ménard, working as an Anthropic researcher, used Claude Science to produce what is reported as the first complete ultraviolet map of the sky.

According to Anthropic's own account, Claude orchestrated agents that merged existing UV datasets from GALEX, Swift, and FIMS/SPEAR, then predicted the roughly one-third of the sky no UV telescope had observed, using relationships to visible, infrared, and radio data.

Anthropic says hidden test regions were reconstructed to within about 10% of real measurements, and each pixel is labeled as measured or predicted with uncertainty estimates. These accuracy claims come from the developer's own report and have not been independently verified. A later Anthropic post describes the work as a teaching tool and says it took a few days rather than the weeks humans would need.

AIWritten by AI from the articles below · overview updated Oct 8, 9:11 PM ET

Check the sources:

Article timeline

Follow the coverage from different perspectives. Times are ET.

Oct 8
  1. Anthropic
    Astrophysicist uses Claude to build first complete ultraviolet sky map

    An astrophysicist worked with Claude Science to create the first complete ultraviolet map of the sky, covering regions never observed in UV. Claude located existing datasets, combined them, and filled gaps with statistical inference, taking a few days rather than weeks of human work. The map is presented as a teaching tool and an example of low-priority scientific work that AI now makes feasible.

  2. Anthropic ResearchPick
    Anthropic researcher builds first complete UV sky map with Claude Science

    Johns Hopkins astrophysicist Brice Ménard, working as an Anthropic researcher, used Claude Science to produce the first complete map of the sky in ultraviolet light. Claude orchestrated agents to merge GALEX, Swift, and FIMS/SPEAR data, then predicted roughly a third of the sky that no UV telescope had observed, using relationships to visible, infrared, and radio data. Hidden test regions were reconstructed to within about 10% of real measurements, and each pixel is labeled measured or predicted with uncertainty estimates.

Heat trend

Not enough continuous observations to show a trend yet.