Coding agents expose this: same VPS, 3 runs, ~65% drift

(webbynode.com)

1 points | by gsgreen 5 hours ago ago

3 comments

  • gsgreen 4 hours ago

    Worth noting: this only shows up with REPEATED runs.

    Single benchmarks often look completely normal.

    That’s why a ton of comparisons/benchmarks miss it. Doing this because that drives me a little nuts.

  • gsgreen 4 hours ago

    [flagged]

  • gsgreen 3 hours ago

    [dead]