SciML lead: Google Antigravity orchestrates 60 parallel issues, outclasses Claude and Codex
ChrisRackauckas · x · 2026-11-18
Chris Rackauckas, core developer of the Julia SciML ecosystem, explains why he swapped Claude for Google Antigravity as the orchestrator of his "personal software factory," backing it up with a GitHub heatmap showing 27,886 contributions in the past year. His comparisons: - Claude imposes artificial limits ("4 workers maximum!"); - Codex is overly pedantic, working one issue at a time — a great code reviewer but a poor orchestrator; - Antigravity tracks 60 issues at once — 30 code changes, 15 waiting on CI, 5 awaiting his decision — checking every 10 minutes and just keeps going. He argues Google's internal use of Antigravity explains why the company is now iterating faster than everyone else, frames it as "build systems, not prompting specific agents" in a "post-prompting world," and says the orchestration gap is like "Fable 5.2 vs Sonnet 4.5 in coding." He notes he holds Claude Max, Codex Max, and Devin Max accounts for open-source programs.
More from coding & agent
- 12 indie AI mini-game devs share real revenue: top Steam title made $42K RMB in 49 days — sujingshen · 2026-11-18
- Oracle agent memory cuts input tokens ~10x at turn 80 vs full chat replay — bibryam · 2026-11-18
- Huawei researcher's Cambridge talk: agent-era code bottlenecks shift to specs and verification — satnam6502 · 2026-11-18
- 50-company study: median enterprise knowledge base doc is 505 days stale, 1 in 65 AI citations hits expired verification — femke_plantinga · 2026-11-18
- Plane AI now writes PQL queries for you, keeping them editable — JosephJacks_ · 2026-11-18
- Qwen3.8-27B OpenCode adapter lifts SWE-Bench Pro 35.3%→51% with 6-8x fewer tokens — yb2698 · 2026-11-18