AI-only speed optimizations make pydegensac 4.7x faster, zero algorithm changes
ducha_aiki · x · 2026-11-11
- duchaaiki shows pydegensac's accuracy-vs-time curves for fundamental matrix estimation (IMC PhotoTourism stpeterssquare, 600 pairs, RootSIFT-8k, single thread).
- From 0.1.2 to 0.3.1, not a single line of the algorithm changed — all speedups came from implementation optimizations by Astra, Fable and Opus; the new version is 4.7x faster at 50k iterations.
- The author's only manual change was adding deterministic seeding in 0.2-0.3. Takeaway: implementation and optimization matter enormously.
More from coding & agent
- n8n Labs launches open-source agent Nod: zero false memories in 216 injection attacks — Aiden_Tech_Ai · 2026-11-11
- Anthropic launches self-hosted Claude Managed Agents in private beta — Claude (Anthropic) · 2026-11-11
- Anthropic launches self-hosted Claude Managed Agents in private beta — danshipper · 2026-11-11
- Codex Remote Chats Now Integrated into All ChatGPT iOS Chats — SIGKITTEN · 2026-11-11
- Cloudflare proposes identity, reputation, accountability frameworks for AI agents on the web — bibryam · 2026-11-11
- banteg launches Sokoban Eval: trilogy solved in 3,000-3,064 keys, last 64-key gap unproven — banteg · 2026-11-11