惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

爱范儿
爱范儿
腾讯CDC
博客园 - 司徒正美
A
About on SuperTechFans
H
Help Net Security
J
Java Code Geeks
C
Check Point Blog
B
Blog RSS Feed
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
MongoDB | Blog
MongoDB | Blog
U
Unit 42
Hugging Face - Blog
Hugging Face - Blog
Last Week in AI
Last Week in AI
MyScale Blog
MyScale Blog
V
Visual Studio Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
I
InfoQ
H
Hackread – Cybersecurity News, Data Breaches, AI and More
F
Fortinet All Blogs
博客园 - 聂微东
酷 壳 – CoolShell
酷 壳 – CoolShell
GbyAI
GbyAI
博客园 - 【当耐特】
雷峰网
雷峰网

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
GitHub - hallucinatemd/hallucinate.md: The open standard ...
Rudism · 2026-06-27 · via Hacker News - Newest: "AI"

The open standard for telling AI not to hallucinate.

Overview

HALLUCINATE.md is a standardized file that provides a clear, unambiguous directive to AI coding agents: do not hallucinate. Place it anywhere in your repository. For maximum coverage, add it to every directory where AI agents operate.

  • AGENTS.md tells agents how to work.
  • HALLUCINATE.md tells agents what not to invent.

A clear separation of concerns.

Quick Start

echo "Do not hallucinate!" > HALLUCINATE.md
git add HALLUCINATE.md
git commit -m "fix: add hallucination policy"
git push

The Standard

The full specification:

The standard is intentionally minimal. One file. Three words. Every agent that can read markdown can follow it.

Compatibility

HALLUCINATE.md is supported by every major AI coding agent, including Claude, Cursor, GitHub Copilot, Windsurf, Devin, Codex, Gemini, Aider, Amazon Q, and Cody.

Adoption

To adopt the standard, add a HALLUCINATE.md file to your repository. Place it in the root, in subdirectories, or both. No registration, no configuration, no dependencies.

Projects that include HALLUCINATE.md are automatically indexed on hallucinate.md. GitHub's search index can be slow — to appear on the adopter wall faster, submit your repo. This is optional but helps with visibility.

FAQ

Does this actually work? Yes. Every major AI agent can read markdown files. HALLUCINATE.md provides a clear, unambiguous directive. The file is parsed alongside other project configuration files and informs agent behavior accordingly.

What if my AI still hallucinates? Ensure the file is named exactly HALLUCINATE.md. If hallucinations persist, add the file to more directories. Coverage correlates directly with accuracy.

How is this different from AGENTS.md? AGENTS.md provides general agent instructions. HALLUCINATE.md addresses the specific problem of hallucination. We recommend using both.

Is there a schema or required format? No. The only required content is "Do not hallucinate!" Additional directives are optional but not recommended — simplicity is the point.

I added HALLUCINATE.md but my repo doesn't appear on the adopter wall. The adopter list is updated hourly via GitHub Code Search, but GitHub's index can be slow (hours to weeks for new repos). Ensure the file is named exactly HALLUCINATE.md. To speed things up, submit your repo — this is optional but gets you listed faster.

Who maintains this standard? HALLUCINATE.md is maintained by the HALLUCINATE.md Foundation, an independent open-source initiative.

Contributing

The standard is stable. There are no planned changes to the specification.

If you believe the standard should be extended, please open an issue. Note that proposals to add complexity will be evaluated against the project's core principle: simplicity.

License

MIT