Safety
If “Insanity is doing the same thing over and over again and expecting different results”, what the heck is Generative AI?
Gary Marcus critiques generative AI by applying the 'insanity' aphorism to highlight repetitive patterns in how these systems operate—suggesting they may be fundamentally limited by repeating the same
Gary Marcus critiques generative AI by applying the "insanity" aphorism to highlight repetitive patterns in how these systems operate—suggesting they may be fundamentally limited by repeating the same computational processes without achieving genuine understanding or novel reasoning. The post likely questions whether current generative AI approaches can truly innovate or if they are trapped in circular logic despite appearing to produce novel outputs. Marcus, a prominent AI skeptic and researcher, uses this framing to challenge assumptions about AI's capabilities and progress.
Source: Gary Marcus (X) | 2026-06-01