Author Notes LLM Writing Still Has Telltale Signs
Dan_Jeffries1 · x · 2026-07-14
An author with 30 years of writing experience notes that while LLMs have improved significantly, stable patterns are still recognizable:
- Common traits include block-style paragraphs and a formulaic "this and then this" progression
- Rare use of contractions, leading to overly formal phrasing
- Flawless grammar, lacking intentional rule-breaking for emphasis
- Occasional disjointed ideas or inserted irrelevant points, leading to incoherent overall arguments
They also observed that many X posts increasingly follow a template: overly long, thin on content in the middle, and heavily relying on colloquial structures like "here’s the thing." The original post cites Marc Andreessen's take—AI writing is already good enough, and the few remaining weird quirks will soon disappear.
More from Models
- Grok 4.5 is now free inside Cursor, the popular AI coding IDE — mark_k · 2026-07-21
- GPT often converges on the same near-miss ideas in math problems — yacineMTB · 2026-07-21
- Eno Reyes says model distillation is basically unstoppable — LangChain · 2026-07-21
- Sakana says multiple diffusion models plus MCTS beat test-time scaling on coding and math — SakanaAILabs · 2026-07-21
- OpenAI hackathon project stalls as Codex struggles on voice, while Claude spots the issue — ColleenMBrady · 2026-07-21
- Kimi K3 lands exactly on China’s 2-year AI capability trend line — peterwildeford · 2026-07-21