跳到正文
prompts.chat · 每日 prompt· Fatih Kadir Akın·· 6 小时前AI 评分20

prompts.chat Book 第一周质量审校:更新前言、历史、导言与第 1 章(全部 17 种语言)

Book quality review, week 1: preface, history, introduction, and chapter 01 (all 17 languages) (#1315) * Book week 1 review: update English preface, history, introduction, and chapter 01 Co-authored-by: Fatih Kadir Akın * Book week 1 review (ar): port English updates and fix translation issues in preface, history, introduction, and chapter 01 Co-authored-by: Fatih Kadir Akın * Book week 1 review (az): port English updates and fix translation issues in preface, history, introduction, and chapter 01 Co-authored-by: Fatih Kadir Akın * Book week 1 review (de): port English updates and fix translation issues in preface, history, introduction, and chapter 01 Co-authored-by: Fatih Kadir Akın * Book week 1 review (el): port English updates and fix translation issues in preface, history, introduction, and chapter 01 Co-authored-by: Fatih Kadir Akın * Book week 1 review (es): port English updates and fix translation issues in preface, history, introduction, and chapter 01 Co-authored-by: Fatih K

来源与原文

prompts.chat · 每日 prompt

作者:Fatih Kadir Akın

发布时间:(北京时间)

阅读原始来源 · github.com ↗
完整链接与内容说明

https://github.com/f/prompts.chat/commit/684e6dfca0bcbee2e0d523fa1525789e78e684e5

本站目前仅有 AI 导读与摘要,未展示原文正文;技术细节、代码和完整结论请查看原始来源。

AI 导读

prompts.chat Book 完成第一周审校,更新英文版前言、历史、导言和第 1 章,并将修订同步到全部 17 种语言版本。内容更新包括:说明 1 token ≈ 4 字符的比例取决于模型的 tokenizer 和语言,上下文窗口数据更新为 GPT-6、Claude Opus 5.5、Gemini 4、DeepSeek V4 均达 1M tokens、Llama 4 为 1M-10M tokens、Mistral Small 4 为 256K tokens,并补充上下文过长时模型可能丢失细节的提示。文生图部分将 DALL-E 替换为 GPT Image,把 "CLIP Guidance" 改为更通用的 "Text Guidance"。

来源:prompts.chat · 每日 prompt · github.com