We wanted the singularity; we got the circularity.

Gary Marcus critiques the gap between AI aspirations and current reality, suggesting that instead of achieving transformative "singularity" breakthroughs, AI development has become cyclical—repeating similar patterns and limitations rather than achieving fundamentally new capabilities. The post likely argues that the field has fallen into repetitive cycles of hype, incremental improvements, and unresolved core problems rather than the revolutionary progress once anticipated.

Source: Gary Marcus (X) | 2026-05-05