DuoDiscover, a Google-Berkeley-Stanford agent project, tops NVIDIA SOL-ExecBench
berkeley_ai · x · 2026-10-16
DuoDiscover, built during a Google internship in collaboration with UC Berkeley and Stanford AI Lab, treats costly evaluation as part of what agents discover, tackling the bottleneck that AI can generate ideas in seconds but testing them takes hours or days.
Results:
- #1 on NVIDIA's SOL-ExecBench
- 2× experts on SWE-fficiency
- 1.92× on vLLM, 1.44× on FreeToken
- 2.68× over production TPU kernels
- Beats the best human- and AI-designed CPU prefetchers
Related event: DuoDiscover Tops NVIDIA SOL-ExecBench, Speeds Up TPU Kernels 2.68x(9 posts)→
More from coding & agent
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Vibe-coded iPhone Duo sniping bot built with Codex in 17 minutes, 41 tests passing — xiaohu · 2026-10-16
- Long-term multiplayer agent memory tool tops BEAM memory benchmark — CurieuxExplorer · 2026-10-16
- NativeCAD ships generative CAD over MCP with 177 tools, 94% of plain-English part requests pass — burhop · 2026-10-16
- Flux.ai imports STEP files and edits existing CAD geometry via natural language — burhop · 2026-10-16
- 50 tasks at once energizes me, says dev, as peer warns AI context-switching causes burnout — zack_overflow · 2026-10-16