Model Releases
Relevant to the comprehension challenge I posed in 2014 and my bet with Miles Brundage.
Relevant to the comprehension challenge I posed in 2014 and my bet with Miles Brundage. We edited Mark Twain's Huckleberry Finn and fed it to 9 AI models to summarize a chapter, twice each. Only Claud
Relevant to the comprehension challenge I posed in 2014 and my bet with Miles Brundage. We edited Mark Twain's Huckleberry Finn and fed it to 9 AI models to summarize a chapter, twice each. Only Claude Fable 5 followed the edited text both times; GPT-5.5 followed it once ↓
Source: Gary Marcus (X) | 2026-10-15