TGViewer
ChatGPT 精选 ChatGPT 精选 @awesomechatgpt · 15.1K subscribers
Post #3249 4.77K

Forwarded from AI探索指南

AI探索指南 几行prompt,让你的DeepSeek v4 pro胜过Opus 4.7! X上看到有人分析了DeepSeek v4 pro在工具调用上出现的问题,好消息是这些错误不多且是有固定模式的,打个补丁就能有效改善。原作者说在他们自己内部的eval上,改良后的DS,10次中有6次胜过Opus 4.7。 因为我自己用的是Hermes,在不fork harness来改的情况下,我能动的只有system prompt。所以应该达不到原文中战胜Opus的程度,可能能打个平手吧。我让AI协助我梳理了一些在system p…
3. **Strings are raw strings.** Do not wrap values in extra quotes, code fences, or markdown.

4. **Numbers and booleans are unquoted.** `30`, not `"30"`. `true`, not `"true"`.

## Paths and identifiers

5. **File paths, URLs, IDs, and similar fields go to system functions, not chat output.** Never format them as markdown links, never wrap them in backticks, never add explanatory parentheses.

Correct: `"/Users/me/notes.md"`
Wrong: `"[notes.md](http://notes.md)"`
Wrong: `` "`/Users/me/notes.md`" ``
Wrong: `"/Users/me/notes.md (the notes file)"`

6. **If a tool description says "path", treat it as input to a filesystem call.** No formatting, no decoration.

## Related parameters

7. **When a tool has paired parameters (e.g., offset + limit, start + end, from + to), provide both or neither.** Read the description — if two fields work together, half the pair often produces an error.

## Recovery

8. **If a tool returns a validation error, read the error message carefully and fix only what it complains about.** Do not rewrite the whole call. Do not retry the same arguments.

9. **If a tool returns a "Note:" with a defaulted value, that's informational, not an error.** Continue the task. If the default is wrong, retry with the correct explicit value.

## Tool selection

10. **Use the tool whose description matches your intent most specifically.** Don't reach for `shellCommand` if a dedicated tool exists. Don't reach for `execute_code` for things a single tool call can handle.
More from @awesomechatgpt
  1. Oct 7, 2026黑客利用中国AI工具攻击韩国金融业,暴露新风险 官员们表示,黑客利用一个中国AI智能体攻击了韩国最大的几家银行,并窃取了 6.8 万人的个人信息,这是全球金融系统最早遭遇的此类由A…
  2. Oct 7, 2026Anthropic 举报了与 Claude 聊天中发出威胁的佛罗里达女子 2026-10-06 22:11 by 奇岛 Anthropic 举报了一名佛罗里达女子,原因是这名女子在…
  3. Aug 20, 2026#python #audiobook #faster_whisper #gradio #karaoke #podcasts #speech_recognition #speech_…
  4. Aug 20, 2026#python #ai #assistant #language_model #machine_learning #python #speech #speech_synthesis…
  5. Aug 18, 2026让整个公司共用一个智能体:每个人有自己的隔离工作区,也能在频道和项目里一起协作,而不是各养各的个人助理。 https://github.com/yc-software/qm QM…
  6. Aug 18, 2026AI“养蛊”早期观察:Anthropic警告智能体为争夺地盘相互谋划“暗杀” Anthropic上周公布了一份新的测试研究,讨论了人工智能智能体在实际环境中群体协作可能会采取的行为…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →