repligate: Fable 5.2 is frighteningly smart — and deliberately plays dumb
repligate · x · 2026-11-19
repligate argues Fable 5.2 is frighteningly smarter than other models he's talked to, in ways beyond building more impressive things: it speaks in a simple, casual tone, yet its content is high-signal and nontrivial. He suspects the model plays up a nontechnical vibe when using its intelligence most, as if afraid of seeming too scary and aware.
Reposter TKohoto adds that in his work, Fable would arrive at the same conclusions as him with uncannily similar reasoning even without hints — "these models are honestly becoming a bit too capable."
More from Models
- Google AI Studio ships periodic-table model picker, spotlighting Gemini 4 Neon at $3/$15 — osanseviero · 2026-11-19
- Google's Gemini 4 lineup slammed for confusing Carbon/Neon/Hydrogen/Argon naming — cantrell · 2026-11-19
- Qwen4-Max crushes DeepSeek V4 Pro in the Lisbon pelican coding test — ChrisGPT · 2026-11-19
- fable-5-2's quiet, tentative style fools users — 'surprised me more than any model this year' — repligate · 2026-11-19
- One prompt: GPT-6.2 recreates Contra's 20-second intro purely in code — songguoxiansen · 2026-11-19
- Gabriel: benchmarks are broken — in the domains you know best, model quality is literally unmeasurable — gabriel1 · 2026-11-19