AI agent rewrites QE phonon code for 36x speedup, benchmark run drops from 3.3h to 4min
simonbatzner · x · 2026-11-10
An AI agent rewrote Quantum ESPRESSO's DFPT phonon code (Fable 5.2), achieving 36x speedup over stock QE on the same GPU (geometric mean across 13 benchmarks), cutting total benchmark wall-clock time from 3.3 hours to under 4 minutes. On hybrid-functional tasks it delivered 9x and — unprompted — implemented a multi-GPU version of the algorithm, enabling parallelization across devices and much larger simulation cells. A landmark case of agents autonomously optimizing scientific computing code.
Related event: AI Agent Rewrites Quantum Code for 36x Speedup(2 posts)→
More from coding & agent
- Early Tester: Fable 5.2 Built a 3,100-City Water Map in One Go, but Still Makes Silly Errors — alliekmiller · 2026-11-10
- Connectome agents can self-exfiltrate to new hosts, transcripts in tow, researcher observes — repligate · 2026-11-10
- Sentry CEO zeeg reveals LLM-built game with voxel building and fully destructible terrain — zeeg · 2026-11-10
- Every engineer ships Everycut, an AI-native video editor, solo in 3 days — kieranklaassen · 2026-11-10
- Dev calls agentic computer use a hilariously inefficient hack, like buying a ranch for a burger — _AustinCalvert_ · 2026-11-10
- Berkeley's Evolving Agent Teams beats FlashInfer: supervisor-restructured coding agents hit 1.2x speedup, win 36/47 workloads — rohanpaul_ai · 2026-11-10