Same model, 63% vs 97% on ARC-AGI-3: 7 harness rules beat max reasoning

victor_explore · x · 2026-09-07

The author argues that the code wrapping a model—the harness—can matter more than the model itself, using ARC-AGI-3 results.

Note: the thread ends with a follow-me plug, but the core claim (harness design over reasoning strength) is backed by data.

Original post →

More from coding & agent

coding & agent channel →