Dev claims benchmarks are meaningless, only 'vibes' separate models

Developer gnukeith claimed benchmarks are meaningless marketing hype and that the only real difference between models is subjective 'vibe', sparking broad discussion about the credibility of AI evaluations.

2026-09-22 ~ 2026-09-22 · 2 related posts

• Dev claims benchmarks are 'absolutely meaningless' — models only differ by vibe — gnukeith · 2026-09-22

1 near-duplicate retellings: gnukeith