Claude burns 24h building cells that take seconds to measure, in overnight benchmark fail

StefanoGogioso · x · 2026-09-04

Stefano Gogioso shares a hilarious overnight agent fail: when asked why the benchmarks weren't done, Claude's own diagnosis was damning — at a 2^24 grid size, each cell took 1-5 hours to build but under 1 second to measure. A 24-hour run yielded only a few hundred microsecond timings.

Beyond the comedy, it's a cautionary tale about letting models autonomously design experiments without any cost-awareness of imbalanced build-vs-measure budgets.

Original post →

More from coding & agent

coding & agent channel →