跳到主要内容 / Skip to main content
GitHub14,554github.com

asgeirtj/system_prompts_leaks

by asgeirtj首次上榜 2026-07-04

摘要

asgeirtj/system_prompts_leaks 是一个 GitHub 项目,它收集了 Anthropic 和 OpenAI 多个大模型的系统提示词,包括 Claude Fable 5、Opus 4.8、ChatGPT 5.5 Thinking 等。这些提示词揭示了模型背后如何被引导、如何设定角色和限制,对 AI 研究者和开发者理解模型行为非常有价值。它引发了关于提示工程和模型安全边界的讨论,也是窥探顶级 AI 内部设计的一个窗口。

近 7 天热度

2026-07-28 · 60,9692026-07-29 · 61,1802026-07-30 · 61,3512026-07-31 · 61,5382026-08-01 · 14,7332026-08-02 · 14,6162026-08-03 · 14,554
07-2808-03
阅读原文

相关推荐

asgeirtj/system_prompts_leaks

Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.

diegosouzapw/OmniRoute

Never stop coding. Free MIT AI gateway: one endpoint, 290+ providers (90+ free), 500+ models — Kimi, Claude, GPT, OpenAI, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 500+ contributors

aiautoawarecavemanclaude

affaan-m/ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

zhaoxuya520/reverse-skill

Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端