// HACKER NEWS — CYBERSECURITY
NanoGPT Speedrun Frontier
We ran 153 autonomous runs across 18 frontier models on the nanoGPT optimizer speedrun.
Give each model's best final run the same resource budget and compare the best validated record it reached within that budget.
Open Traces to explore 41 curated full agent trajectories, including tool calls, subagents, and scratchpads.