算法缺陷 (2 articles)

Claude 4.6 Version Crashes: The Algorithmic Black Hole Behind a 23-Point Plunge

While everyone celebrates Claude's 38.3-point programming improvement, a more dangerous signal has been masked: stability plummeted from 54.2 to 31.2 points, revealing a systemic algorithmic collapse rather than normal performance fluctuation.

Grok 3's Logic Score Plummets to Zero: Five Letters Expose Fatal Algorithm Flaw

Grok 3's logic reasoning score collapsed from 100 to 0 in the latest YZ Index evaluation, exposing a systemic failure in the model's reasoning capabilities despite improvements in other areas.