Tester: Astra is "autistic" at parsing human sentiment; Fable and Opus run circles around it

teortaxesTex · x · 2026-09-26

After running his usual "explain" sentiment tests, user teortaxesTex says Astra is the first model showing such a massive deficiency in this dimension: "It does not try to parse human sentiment whatsoever," while Fable and Opus run circles around it.

A third-party behavioral observation on models' emotional/social intelligence — a useful data point for model comparisons beyond benchmarks.

Original post →

More from Models

Models channel →