STOKE: Stanford's superoptimizer finds optimal assembly through randomness with early pruning
lauriewired · x · 2026-10-13
Security researcher lauriewired explains STOKE, Stanford's superoptimizer that randomly mutates a program's assembly to search for optimal machine code — 99%+ of candidates are wrong, but it occasionally finds dramatic wins. STOKE isn't purely random: it rejects bad-looking branches early to concentrate compute on promising paths. The attached figure shows STOKE seeing through gcc -O3's literal translation of a cycling-through-3-values benchmark and rediscovering the intuitive algorithm using conditional moves.
More from Research
- BudgetPix: adaptive tokenization matches pixel diffusion fidelity with just 25% of the compute — Ozgur Kara · 2026-10-13
- DeepMind's AlphaProof Nexus Paper Published in Science Magazine — swarat · 2026-10-13
- Google published 90 peer-reviewed disease papers in 5 years, 90k+ citations — ymatias · 2026-10-13
- Sakana AI and Berkeley propose MASS: multi-agent self-supervision for recursive self-improvement — TheTuringPost · 2026-10-13
- AI forecasts patient physiology to optimise IV-to-oral antibiotic switching, published in Nature Communications — ai_ucl · 2026-10-13
- 60.6% of LLM theorem rewrites silently drop hidden hypotheses, study finds — MFarajtabar · 2026-10-13