Phase 2 of my heuristic-learning ImageNet-10 experiment:

Phase 2 of my heuristic-learning ImageNet-10 experiment: Inspired by @Trinkle23897 's “Learning Beyond Gradients,” I used Claude Code + Codex to iteratively improve a pure symbolic vision system. No neural nets. No backprop. Just visual
Ranked #42 on backlist 2026-05-25 (25 May 2026 UTC) · by (Eason) ·

How it ranks: Backlist reads my Twitter/X timeline, scores every tweet for substance with an LLM rubric (not engagement), and publishes the daily top picks with a one-line takeaway. Curated by Surya Dantuluri.