Months of tuning LLMs for news writing: facts are easy, monotony is hard
ivan_bezdomny · x · 2026-08-22
Responding to Ethan Mollick's point that lack of stylistic variety is crippling LLM writing, the author shares months of first-hand experience tuning LLMs for news: it works, but the model settles into patterns and formulas.
Getting facts and ordering right is much easier than making headlines fun without monotony. Mollick argues that prompting only gets you so far — real variation is needed and under-researched.
Related event: LLMs Still Struggle with Monotonous Writing Style(3 posts)→
More from Models
- GLM 5.5 rumored to drop soon, coding ability expected to match frontier models — bindureddy · 2026-10-16
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16
- DIY benchmark ranks 18 models on subjective judgments, GLM-5.3 tops consensus match — arkuto · 2026-10-16
- Bindu Reddy: Google's Argon excels at complex doc writing at half the cost of Opus — bindureddy · 2026-10-16
- MAI-2 is 2x bigger than V4-Pro while V4.1F is 3x smaller: Microsoft's scaling ladder questioned — teortaxesTex · 2026-10-16
- Step 5 Preview hits DeepInfra day-zero: 600B MoE, 1M context, $1/M input tokens — StepFun_ai · 2026-10-16