Researcher teases dynamic composite eval index as "evals run on Twitter vibes"

evijit · x · 2026-09-04

Researcher evijit criticizes AI eval culture as running on "Twitter vibes" — composite indices like AA are only praised until Astra tops them. He is building a more dynamic composite eval index method using EvalEval data, with results coming soon.

Original post →

More from Models

Models channel →