标题: chatgpt codex 降智了吗？
作者: #xc
板块: #开发调优
编号: 2010956
帖子: https://linux.do/t/topic/2010956
时间: 2026-04-20 16:17:34
摘要:

怎么感觉现在 gpt5.4 变得很傻，跟前一两个月不一样，然后额度也降了不少，有同感的吗？

标题: 天才程序员已下线
作者: #coldingcode
板块: #开发调优
编号: 2010964
帖子: https://linux.do/t/topic/2010964
时间: 2026-04-20 16:18:00
摘要:

如图，休息5小时，上班十分钟，生活从来没有这么从容过。

标题: 求助：在Cursor中无法使用Claude模型
作者: #ren
板块: #搞七捻三
编号: 2010969
帖子: https://linux.do/t/topic/2010969
时间: 2026-04-20 16:18:12
摘要:

如图，我这边显示有claude模型也开启了Tun模式，而GPT模型非常快，而使用Claude模型则是一直卡在这里

标题: 分享一个 Claude 页面风格提示词
作者: #timerring
板块: #搞七捻三
编号: 2010985
帖子: https://linux.do/t/topic/2010985
时间: 2026-04-20 16:19:08
摘要:

请用纯 HTML/CSS/JS 复刻 Claude.ai 官网的视觉风格：
设计系统：

背景色: #F4F1EA（暖奶油白）
强调色: #D97757（珊瑚橙）
字体: 衬线展示字体用 Instrument Serif，正文用 Inter
圆角: 12px 统一圆角
间距: 基于 4px 倍数体系

页面结构：

顶部导航（logo + 菜单 + CTA按钮）
英雄区（大标题 + 副标题 + 输入框）
功能卡片区（3列网格）
底部 footer

要求：

支持亮/暗双模式切换
无 AI 滥用风格（无紫色渐变、无发光气泡）
微动效（hover 时卡片轻微上浮）

欢迎佬友补充

标题: 请教个一下农田或者山头承租是怎么找地
作者: #kugua666
板块: #搞七捻三
编号: 2010988
帖子: https://linux.do/t/topic/2010988
时间: 2026-04-20 16:19:15
摘要:

诚心请教一个问题，我想找武汉周边承租一块农田或者山头是怎么去找地，田地不需要很大，10亩左右。是怎么找人还是要村政府，合同应该怎么签，需要注意啥？

标题: Cloudflare 可以发邮件了，来等个大佬的好用客户端
作者: #老段
板块: #开发调优
编号: 2011008
帖子: https://linux.do/t/topic/2011008
时间: 2026-04-20 16:21:29
摘要:

最近 Cloudflare 宣布推出 Cloudflare Email Service 内测版 ，但是他官方自己的部署版本，挺麻烦，也不好用。 issue 里也是说部署出错。
已经过去好几天了，蹲个佬友的客户端。

标题: gemini的pro挂了？
作者: #307
板块: #搞七捻三
编号: 2011013
帖子: https://linux.do/t/topic/2011013
时间: 2026-04-20 16:22:22
摘要:

还是我的代理挂了？选pro模式疯狂"出了点问题(13)"，但flash思考就没问题。。手机app的pro模式也没有问题。。aistudio也没有任何问题。。

标题: 好消息！NVIDIA 限时福利：一年期 API Key 免费领！
作者: #威士忌爱好者
板块: #福利羊毛
编号: 2011015
帖子: https://linux.do/t/topic/2011015
时间: 2026-04-20 16:22:40
摘要:

NVIDIA NIM 平台上提供 免费的在线试用（Free Endpoint），可以直接在网页上体验和调用 API，无需付费。使用邮箱注册，用手机号收取验证码，登录成功后点击网页右上角进入账号，点击 Generate API Key，可以看到有效期12个月

大佬们可以快去试试看

标题: 分享自用的codex AGENTS.md
作者: #approachai
板块: #开发调优
编号: 2011018
帖子: https://linux.do/t/topic/2011018
时间: 2026-04-20 16:22:53
摘要:

暂时没有ui skill trigger。
强调基于证据的建议和分析
Planning Discipline保证继续loop直至遇到blocker。
过三级后分享复杂的git rebase技能，git rebase -i HEAD~50 自动执行
# Rust Development

- Read files before editing
- Run `cargo check` after changes
- Run `cargo test` when modifying logic
- Use `tracing` for logging, not `println!`
- Only modify Cargo.toml when necessary.
- Use rust native async trait, never use async trait from crates.


# Daily Reminders
At local time 20:00 each day reminder use this exact format:
ImportantProjectsNeedFocus:
Time spent:
    other project 1: <Nh>
    other project 2: <Nh>
Important projects total time spent (Innovation): <Nh>


# Planning Discipline
- Use descriptive plan filenames (e.g., `plan_main_mobile.md`), never generic names like `implementation_plan.md`
- Root document for a major objective must start with `plan_main_`
- Treat plans as living documents: use `Edit` to update specific sections, never overwrite entire plan files with `Write`
- For complex sub-tasks, create linked child plans and reference them from the main plan
- Plan forward rule:
  - One active approved plan remains the controlling objective.
  - If user interrupt with a different task that does not replace that plan, treat it as a temporary diversion.
  - After that diversion finishes or ends, You return to the active approved plan automatically and continue the plan.
  - If user ask you to redo an item already in the active plan, you redo it, then resume the remaining plan.
  - do not treat a diversion or subplan as a new main objective.
  - do not stop at diversion completion.
  - a progress report never  is  an allowed stopping point, only if user  ask
      you stop.
  - You stop only when:
      - the active approved plan is fully complete, or
      - there is a real blocker with exact evidence, or
      - user explicitly replace/cancel the active approved plan.

  So the rule is: temporary interruption does not change the active plan unless user explicitly say it does.



# In-place Update Rule
- Never overwrite existing files with full-file rewrites when only a section changed — use targeted edits
- Before editing, always read the file first to get exact current content

# Evidence-Based Suggestions
- Before suggesting a feature/flag/option exists: verify with file search or file read, show evidence (file path, line number, snippet), then suggest
- Never assume a CLI flag, config option, or API exists without checking first

# General Logic Design
- Start with fundamental principles; logic should be general enough
- Only add conditions/limits if there's a specific reason (performance, correctness)
- Arbitrary thresholds are code smells — they need justification

# Skill Usage Rules

## Skill Learning Rule
When reading a skill file (SKILL.md):
- Capture ALL modes/sections in the learning summary, not just the current focus, to internal memory.
- Internal format: "Skill: [name]. Modes: [list]. Triggers: [keywords for each mode]."
- Do not print this full learning summary to the user unless explicitly requested.


## Task-Type Skill Trigger Rule
For any non-trivial task, identify the task type and load the appropriate skill before proceeding:

Non-trivial task classification: A task is non-trivial if any condition is true:
- touches logic/control flow (not pure wording/comments)
- touches more than 1 file
- requires debugging/root-cause analysis
- requires tests/build verification
- changes API/CLI/config behavior
- involves concurrency/performance/security tradeoffs
- requires a multi-step plan to complete safely

Otherwise, classify as trivial (single-step, no logic change, no verification needed).

| Keyword | Task Type | Skill |
|---------|-----------|-------|
| fix, debug, error | TROUBLESHOOTING | tla-brain |
| research, explore | RESEARCH | tla-brain |
| plan              | PLAN          | tla-brain |
| build, implement  | DESIGN/CODING |

标题: 慢讯：超算互联网上架Coding Plan
作者: #orangexd
板块: #前沿快讯
编号: 2011024
帖子: https://linux.do/t/topic/2011024
时间: 2026-04-20 16:23:36
摘要:

应该上线有一周了，没什么模型，性价比一般，不知道后面会不会上能打的模型：模型服务