Engineer says manual tweaks after Claude optimization made EC2 CPU 50x faster than M4 Max
_Stocko_ · x · 2026-11-05
Developer Stocko reports that after Claude "optimized" his feature extraction routine, he applied his own tuning on top and got it running 50x faster on an EC2 CPU instance than on his M4 Max. His takeaway: real software engineers know low-level "incantations" that vibe coders don't — human expertise after AI output remains decisive.
More from coding & agent
- Revolut cut AI coding inference costs ~90% by self-hosting GLM on 56 B200s instead of Claude — sebkrier · 2026-11-05
- VibeCoding a 3D fishing game in 4 days with Kimi K3.1 Pro and DeepSeek: full workflow breakdown — lxfater · 2026-11-05
- Sentry founder says AI agent 'junior' handles hardest coding tasks well — zeeg · 2026-11-05
- How Codex Happened: Inside OpenAI's coding comeback from failed launch to ChatGPT centerpiece — danshipper · 2026-11-05
- Tencent Hunyuan Hy4 lands in OpenClaw with vision, 1M-token context, agent gains — TencentHunyuan · 2026-11-05
- Dev shows Claude Code workflow that builds sites with no obvious 'AI slop' — randomname11111_ · 2026-11-05