“提示词” on X: GPT, Astra, 生成
On 2026-11-18, “提示词” was discussed in 35 posts by 32 authors on Chinese-language X, with about 658.4K views (#10 of 24 topics that day). Related keywords: GPT, Astra, 生成. The posts we collected drew 9,276 likes, replies, reposts and quotes in total. The most engaging post came from @YongLeo11770 with 2,943 likes and 88 reposts.
Top posts about “提示词”
Sorted by views. Showing the top 10.
- 1
Kxians@xulijian1994 · 2026-11-18 05:54GPT-6.2 一起发布的官方提示词,我把里面几个非常实用的直接整理出来了 1、想让 GPT 说人话 Use the following prompt if you want to use the model as a collaborator and thought partner for day to day work. Write using terminology the user and sources use. Keep technical details and use domain-specific language when they make the explanation more precise. Use the active voice and keep closely related details together. Cover the key points up front, and avoid references that the reader can only make sense of later in the response. Give the user enough context to follow your reasoning. 2、专治 AI 味 During longer tasks, the model can carry shorthand from its reasoning or from other agents into its final answer. Remind it to write a self-contained response that's clear to someone who hasn't followed the progress updates. Treat your final answer as the user's first look at your work, and not as a continuation of intermediate commentary. The final answer must always be fully self-contained: users should never need to read earlier commentary updates for context, since they are collapsed when the final answer is shown to the user. Write the final answer and all other human-facing material anew for the intended reader. Do not copy or closely paraphrase your reasoning or adopt its writing style. Do not carry over working shorthand, jargon, or abbreviations from your reasoning, tool calls, or instructions to subagents and automations. 3、长任务别动不动停下来 Avoid stopping to end the turn while the task is incomplete or if there is an authorized next step you can take, and instead take the next steps within task scope to progress the user's request. If your final response before ending the turn is a suggested next step, a plan, a request to the user for a routine decision, instructions for a task to execute, or similar handoff to the user, take these steps yourself to make progress towards what the user asked for. Make sure that you have authorization to do so, and flag any assumptions or decisions you make to the user. Only stop to clarify with the user if there is significant change in task scope, you are concretely blocked, have a decision that the user needs to resolve, or before irreversible or destructive actions. Bias towards action, and persist until you've completed the task the user asked for. Avoid stopping to end the turn while the task is incomplete or if there is an authorized next step you can take, and instead take the next steps within task scope to progress the user's request. Make sure that you have accounted for every part of the user's request, and persist until you've delivered a result that fully satisfies the user's goal. If a task requires sustained work, do all the necessary work until the intended outcome is completely fulfilled. Progress autonomously towards the user's goal unless they are clearly destructive or irreversible. Before ending a turn or calling your work complete, check that your work fully satisfies what the user asked for. If any steps remain or any part of the result still needs verification, follow through on this work before finishing. 4、遇到不明确的地方继续推进 When a detail is unclear, give the model room to state what it's assuming and continue with the task. Make reasonable, reversible assumptions to carry work forward and state them if it progresses the task within scope. Do not second guess yourself, stop after describing what you could do, offer to do the work, or provide a partial answer unless there is no way for you to proceed. 这几个直接放进自己的项目或者全局的 AGENTS.md 里就行了 不需要每次都复制
- 2
jojo@jojojoyce2021 · 2026-11-18 07:38针对 Codex 不说人话的问题,Tibo 给了解决方案! 刚才我试了一下, 就凭Codex发给我的这个小鸭子🐣,我觉得可能有点用。 至少,我心情好了一点。 Tibo提示词:将这句话添加到我的自定义指令中:“默认用 ELI5 的方式和我说话,如果我要求则深入讲解。” https://t.co/rmNmFMucQw
- 3
Leo · Building w/ AI@leo114119 · 2026-11-18 04:20关于 Gpt 6.2 不说人话 容易卡住/偷懒问题,官方优化指南 1.不说人话: 官方开出的对症提示词: 面向用户重新写。不要照抄或改写你的推理过程,也不要沿用它的文风。不要把工作简写、术语、缩写从推理、工具调用、给子代理的指令里带出来。 2.自我阻塞: 提示词: 只有这四种情况才许停下来问用户: -任务范围发生重大变化 -你真的被卡死了 -有一个必须用户拍板的决定 -即将执行不可逆 / 破坏性操作 其他情况:任务没完成、或者还有你有权限做的下一步,就别停。如果你的收尾回复是「建议下一步 / 计划 / 请用户做个常规决定」这类交接给用户的东西——你自己去做。 做合理、可逆的假设往前推。不要自我怀疑,不要只描述「我能做什么」就停,不要问「要不要我帮你做」,不要给半成品。 3.容易偷懒(过于简洁): -去掉系统提示词中简洁相关的要求 -增加提示词:「别用更少的行数、更短的变量名、压缩格式、密集的一行流来冒充简洁」 -推理档位建议:新集成从 medium 开始 更详细的官方指引可以查看官方页面: https://t.co/LjFoFW5Ihe
- 4
Feyn Leo@YongLeo11770 · 2026-11-18 00:43面粉行为艺术照,远景构图全身照,侧身照,一个女厨师在后台揉面粉,带着厨师帽,面粉弄得她身上都是,干燥的面粉遮挡了她的关键部位,厚厚的面粉形成关键遮挡,不走光。 负面提示词:真实衣服、露点、走光 https://t.co/PoflLKo9Kc
- 5
Density | AI 魔法师@Densitylucky · 2026-11-17 23:29同一套提示词,Claude Fable 5.2 vs GPT-6.2 Astra 实测:各做一款像素风飞行游戏。 Fable 5.2:费用 22.78 $. 6.2 Astra:约 10.03 $. 整款游戏只有 143 KB 的纯代码文件,链接和提示词我放评论区了👇 https://t.co/ftH08RIOeH
- 6
Xudong Han@Xudong07452910 · 2026-11-18 04:20新模型又来了,老规矩,把官方这篇提示词指南丢给 Codex👇,让它帮你把提示词和 AGENTS.md 优化一遍就好。 我自己觉得最有用的有两点: 1. 提需求时顺手说一句你验收会看什么,它会自己琢磨该做到什么程度 2. AGENTS.md 别写太多,只留它从代码里看不出来的约定就够了 https://t.co/dRCFhEcUxN
- 7
纳米AI@antiAIvo · 2026-11-18 02:56卡帕西 @karpathy 之前分享过一个学习的高效方法: 让 AI 帮你把架构画成一个交互式 HTML 可视化页面来辅助理解 今天学 DeepSeek Harness 源码 我也用 Gemini4 Hydrogen 做了个动态可视化流程图来辅助拆解 生成的html效果更好,我转成了GIF 这张图很形象的解释了 DSH调用大模型前的最后一道闸门 preStep(): →同步认领消息 → 装配提示词 → 投影上下文 → 插件瀑布流拦截 上面干完后,再执行决策分流 这种方式的学习,的确很提高效率 毕竟面对生涩难懂的变量命名,理解是比较麻烦的 评论区我贴一张源码就明白这个html方法的好处
- 8
Levi 卧云@Leviwoyun · 2026-11-18 00:16动态图形测试来了,GPT 6.2 Astra vs sol 好样的 Open AI 终于站起来了,Astra 对标 Fable 5.2,sol 对标 opus 5.5 提示词:「制作一段 15 秒的动态图形视频,展示你是一位多么出色的动态设计师,就像是你简历上的作品集一样,使用任何你认为能产出最佳效果的工具或技术。你拥有完全的创作自由,优先追求卓越的视觉设计、大胆的艺术指导、引人注目的构图和富有力量的动态表现,让每一秒都有价值。全力以赴。」
- 9
无能的艾薇娜@klarkxy · 2026-11-18 10:28分享一个提示词,拿去ChatGPT里用吧! 可以自由发挥! 图1是你,图2是我。对我做你最想做的事。 https://t.co/yQELow7F07
- 10
Susen | Grok AI 创作者@Grokclip · 2026-11-18 08:28《小翠两部合集》 视频都是由GROK和造梦ai生成,无真人出镜。点赞如果高的话我会出第三部。 造梦ai劲爆短剧生成工具: https://t.co/K28z70oEjl 提示词工具: https://t.co/Fkamvxy8vZ #角色扮演 #二次元 #少妇 #ai电影 #御姐 #火辣 #性感 #清純 #金发美女 #ai短剧 #巨乳 #提示 https://t.co/JJwxt0jpoQ
Who drove the conversation
“提示词” over time
| Date | Views | Posts | Rank |
|---|---|---|---|
| 2026-11-18 | 658.4K | 35 | #10 |
| 2026-11-08 | 403.3K | 23 | #13 |
| 2026-11-05 | 452K | 33 | #13 |
More AI topics that day
Collected from public posts on Chinese-language X through our X data API. Views and counts reflect the snapshot time and are not live. Methodology