Follow-up testing: GPT 6.2 stacks jargon on long requests, 'lacking theory of mind' for its reader

johnowhitaker · x · 2026-11-20

johnowhitaker reports on overnight tests of GPT 6.2 with longer, more ambitious requests: results lean heavily on terminology that makes no sense without context, showing little 'theory of mind' for the reader. Consistent with the thread's earlier take — it works best as a programmer's/subagent model with well-specified tasks, and falters on open-ended asks.

Related event: GPT-6.2 Reviews Split: Testers Find It Faster, Critics Blamed for Misuse(5 posts)→

Original post →

More from Models

Models channel →