LLMs can't write for humans: they miss audience awareness and linear idea flow
abeirami · x · 2026-09-11
作者 abeirami 指出 LLM 在整体理解文本上很强,但写作方式与人类作者不同,具体短板有二:
- 不懂受众:模型难以判断文章是否在正式展开之前,先补齐目标读者仍缺失的上下文。
- 缺乏线性推进:模型搞不清概念是否按顺序递进,比如某个术语/符号在首次使用前是否已有定义。
作者认为,模型「不知道自己不知道什么」,因此既发现不了这些问题,也无法修正,最终写不出真正为人类读者服务的文章。
Related event: Developers Say LLMs Don't Read Like Humans, Leaving Two Key Writing Gaps(2 posts)→
More from Models
- Sakana ships Fugu Max and Fugu Ultra v2, pushing the price-performance Pareto frontier via orchestration — SakanaAILabs · 2026-09-11
- Qwen's Justin Lin: arch complexity hides issues evals can't catch, but agentic gains may be worth it — JustinLin610 · 2026-09-11
- OpenAI Shows GPT-6 'Astra' Autonomously Building a Font Playground — OpenAI · 2026-09-11
- European Math Society hails OpenAI's Navier–Stokes solution, flags closed-model access concern — i_dg23 · 2026-09-11
- Blogger swaps in Gemini 3.8 Flash as writing model, says it beats Opus 4.6 with no AI flavor — xiaohu · 2026-09-11
- iFlytek's Spark X2.5 trained on 10,000 domestic Ascend 910B GPUs with 97% uptime — 机器之心 · 2026-09-11