Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Claude Opus 4.1. Parent comment
LLMs are non-deterministic, I think benchmarks should be more about averages of N runs, rather than single shot experiments.
There are no comments on this comment yet.
LLMs are non-deterministic, I think benchmarks should be more about averages of N runs, rather than single shot experiments.