Mollick: Fable's Florid Style Ruins Software Design
emollick · x · 2026-07-08
AI researcher Ethan Mollick points out that Anthropic's Fable model suffers from a persistent "florid writing style" that bleeds into otherwise excellent software and design projects. Even with explicit instructions to avoid it, flowery phrasing still sneaks into prompt text, toasts, and menus—and once it infiltrates, it is extremely difficult to completely eradicate.
Related event: Fable and GPT Criticized for Overly Flowery Prose and Over-explanation(2 posts)→
More from Models
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11