Older models for technical writing?
英文标题：Older models for technical writing?
The new models like Qwen3.8 27B and DeepSeek V4 Flash etc., all have this terrible, Claude-sounding writing style that I can't stand. Here's an example of what I'm talking about: "A probe that asks what a language model memorised reports a null when the model answers at chance, and that null is evid
打开原文相关 2 · 机会 0
中文
The new models like Qwen3.8 27B and DeepSeek V4 Flash etc., all have this terrible, Claude-sounding writing style that I can't stand. Here's an example of what I'm talking about: "A probe that asks what a language model memorised reports a null when the model answers at chance, and that null is evid
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
The new models like Qwen3.8 27B and DeepSeek V4 Flash etc., all have this terrible, Claude-sounding writing style that I can't stand. Here's an example of what I'm talking about: "A probe that asks what a language model memorised reports a null when the model answers at chance, and that null is evid