GPT-6 Astra one-shots a planetarium app; the killer feature was a light-pollution toggle
mhmazur · x · 2026-09-09
A developer used GPT-6 Astra to build a lightweight planetarium web app for teaching kids star and constellation names. Astra one-shotted a flawlessly working initial version, but real value came from iteration — most notably adding a light-pollution adjustment: from his suburban home, 95% of mapped stars were invisible, and the "Suburban sky" setting made the map almost perfectly match what he could actually see. He also added toggles for constellations and labels to make orientation easier. The app is publicly available.
More from coding & agent
- Apodex open-sources FrontierAgent agent framework and ships 35B open-weight Apodex 1.1 mini — mhdfaran · 2026-09-09
- Apodex open-sources FrontierAgent: local multi-agent TUI framework with ReAct and Agent Team modes — mhdfaran · 2026-09-09
- FrontierAgent splits generation from verification, flagging weak evidence before delivery — mhdfaran · 2026-09-09
- Apodex 1.1 rebuilds deep research around files, method selection and verifiable conclusions — mhdfaran · 2026-09-09
- Hands-on with Apodex 1.1: changing requirements mid-run reorganizes the multi-agent task board — mhdfaran · 2026-09-09
- User Puts Apodex 1.1 to the Test: It Reorganizes Work Mid-Run When Requirements Change — mhdfaran · 2026-09-09