Carbon finally took over the code this researcher thought only he could write
iskander · x · 2026-11-20
The turning point of @iskander's thread: progress had been really slow, and this immunology model was the one piece of software he'd have written by hand if he had the time. Then Carbon actually pulled it together — running coherent, reasonable experiments to improve weak outputs without ruining good ones.
This was the moment he shifted from "must write it myself" to "can finally delegate," with follow-up posts comparing how other models handled the same codebase.
Related event: Researcher pits multiple AI models on immunology code with striking gaps(4 posts)→
More from coding & agent
- A 2026 company is just a folder: every department as .md agent files — mdancho84 · 2026-11-20
- Google AI Studio can now build Android apps from a prompt and install them privately, no Play Store listing needed — TawohAwa · 2026-11-20
- No task tracker fits agentic dev: 10-100 concurrent tasks need new patterns — bigblueboo · 2026-11-20
- SelfGraph: open-source versioned knowledge graphs for AI agents over any graph DB — JeremyCMorgan · 2026-11-20
- Why one researcher's immunology model was the code he'd only ever write by hand — iskander · 2026-11-20
- SoduWork: open-source agent workbench adds AI review + human approval to verify agent output — soloboy4567 · 2026-11-20