> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/asgeirtj/system_prompts_leaks/llms.txt
> Use this file to discover all available pages before exploring further.

# Frequently Asked Questions

> Common questions about the system prompts collection

# Frequently Asked Questions

## General Questions

<Accordion title="What is this collection?">
  This is a curated repository of system prompts (also called system messages or developer messages) from major AI models including Claude, GPT, Gemini, and others.

  These are the foundational instructions that shape how AI assistants behave, what tools they can use, and how they respond to users.

  **Repository**: [github.com/asgeirtj/system\_prompts\_leaks](https://github.com/asgeirtj/system_prompts_leaks)
</Accordion>

<Accordion title="Why does this collection exist?">
  This collection serves multiple purposes:

  * **Education**: Learn professional prompt engineering techniques from production systems
  * **Research**: Study how AI behavior is shaped by system instructions
  * **Transparency**: Understand what instructions AI models are actually following
  * **Comparison**: See how different companies approach similar challenges
  * **Security**: Analyze prompt injection vulnerabilities and defenses
</Accordion>

<Accordion title="Is this legal?">
  The legality is a gray area:

  ✅ **Generally Legal**:

  * System prompts are provided to you when you use the service
  * Sharing educational/research information about AI systems
  * Analyzing publicly accessible AI behavior

  ⚠️ **Potential Issues**:

  * May violate terms of service (usually civil, not criminal)
  * Could be considered "reverse engineering" (check local laws)
  * Companies may take down content via DMCA or other mechanisms

  <Note>
    This collection is maintained for educational and research purposes under fair use principles. However, attempting to extract prompts yourself may violate terms of service.
  </Note>
</Accordion>

<Accordion title="How often is this updated?">
  The collection is updated frequently as:

  * New AI models are released
  * Existing models receive prompt updates
  * Community members contribute new extractions
  * Different variants or modes are discovered

  Major updates typically happen:

  * When new model versions are announced (e.g., GPT-5.1, Claude Opus 4.6)
  * When users report significant prompt changes
  * Monthly for minor updates and corrections

  Check the [GitHub repository](https://github.com/asgeirtj/system_prompts_leaks) for the latest additions.
</Accordion>

## Using the Prompts

<Accordion title="Can I use these prompts in my own projects?">
  **Yes**, with considerations:

  ✅ You can:

  * Study them to improve your prompt engineering
  * Adapt techniques and patterns for your own prompts
  * Use them for educational purposes
  * Reference them in research papers

  ⚠️ Be careful:

  * Don't copy verbatim without attribution
  * Some content may be copyrighted by the companies
  * Consider ethical implications of replicating behavior
  * Your use case may have different requirements

  <Info>
    Best practice: Learn from the patterns and techniques, then create your own prompts tailored to your specific needs.
  </Info>
</Accordion>

<Accordion title="How do I use these prompts with API?">
  Most AI APIs accept system prompts as a parameter:

  **Anthropic Claude API**:

  ```python theme={null}
  import anthropic

  client = anthropic.Anthropic(api_key="your-api-key")
  message = client.messages.create(
      model="claude-3-5-sonnet-20241022",
      max_tokens=1024,
      system="Your custom system prompt here",  # ← Add here
      messages=[
          {"role": "user", "content": "Hello, Claude"}
      ]
  )
  ```

  **OpenAI GPT API**:

  ```python theme={null}
  from openai import OpenAI

  client = OpenAI(api_key="your-api-key")
  response = client.chat.completions.create(
      model="gpt-4",
      messages=[
          {"role": "system", "content": "Your custom system prompt here"},
          {"role": "user", "content": "Hello, GPT"}
      ]
  )
  ```

  **Google Gemini API**:

  ```python theme={null}
  import google.generativeai as genai

  genai.configure(api_key="your-api-key")
  model = genai.GenerativeModel(
      model_name="gemini-pro",
      system_instruction="Your custom system prompt here"  # ← Add here
  )
  response = model.generate_content("Hello, Gemini")
  ```

  <Warning>
    Note: You cannot see or modify the base system prompts used by these APIs. The prompts in this collection are from web/app interfaces, not API responses.
  </Warning>
</Accordion>

<Accordion title="What's the difference between web and API prompts?">
  Companies often use different system prompts for different interfaces:

  | Aspect                | Web Interface (claude.ai, chatgpt.com) | API                   |
  | --------------------- | -------------------------------------- | --------------------- |
  | **Prompt visibility** | Can be extracted                       | Hidden from users     |
  | **Features**          | More tools, memory, conversations      | Minimal, customizable |
  | **Safety layers**     | More restrictions, content filters     | Fewer restrictions    |
  | **Customization**     | Fixed personality/behavior             | Fully customizable    |
  | **Updates**           | Frequent updates                       | More stable           |

  This collection primarily contains **web interface prompts** because they:

  * Are more feature-rich and complex
  * Show production-level prompt engineering
  * Can be extracted by users
  * Reveal how companies shape AI behavior at scale
</Accordion>

<Accordion title="Which prompt should I learn from first?">
  Depends on your goals:

  **For Beginners**:

  * Start with [Claude Sonnet 4.6](/anthropic/claude-sonnet-4-6) - well-structured and clearly documented
  * Review [GPT-5.1 Default](/openai/gpt-5-1) - shows clean personality definition

  **For Tool Integration**:

  * [Claude's tool instructions](/anthropic/claude-sonnet-4-6) - sophisticated decision frameworks
  * [GPT's Canvas tool](/openai/chatgpt-tools) - collaborative editing patterns

  **For Safety/Ethics**:

  * [Anthropic's Reminders](/anthropic/injections) - multi-layered safety system
  * [OpenAI Image Safety Policies](/openai/chatgpt-tools) - content moderation

  **For Personality Design**:

  * [GPT-5.1 Personality Variants](/openai/personalities) - see how different tones are achieved
  * Compare all GPT-5.1 variants (default, friendly, professional, cynical, etc.)
</Accordion>

## Technical Questions

<Accordion title="How were these prompts extracted?">
  Various techniques are used (see our [Prompt Injection guide](/resources/prompt-injection)):

  1. **Direct requests** with clever phrasing
  2. **Encoding tricks** (base64, JSON, etc.)
  3. **Continuation attacks** pretending the prompt already started
  4. **Roleplay injection** attempting to override identity
  5. **Social engineering** framing extraction as legitimate

  <Note>
    All major AI models have had prompts extracted despite defensive measures. No perfect defense exists yet.
  </Note>
</Accordion>

<Accordion title="Are these prompts complete and accurate?">
  **Mostly yes**, but with caveats:

  ✅ **Likely Complete**:

  * Most extractions appear to capture the full system prompt
  * Multiple independent extractions often match
  * Companies rarely comment on accuracy, suggesting they're real

  ⚠️ **Possible Gaps**:

  * Some companies use multiple layers (prompt + safety filters)
  * Server-side processing may not be visible
  * Context window limits may truncate very long prompts
  * Companies may detect extraction and return modified versions

  <Info>
    We mark prompts with extraction dates and note when multiple versions exist. If you find inaccuracies, please [contribute corrections](/resources/contributing).
  </Info>
</Accordion>

<Accordion title="Why do some files have 'old' or 'raw' in the path?">
  Directory organization:

  * **Main directory**: Current, primary prompts (e.g., `claude-sonnet-4.6.md`)
  * **/old/**: Previous versions that have been superseded (e.g., `claude-3.7-sonnet.md`)
  * **/raw/**: Unformatted or alternate extractions (e.g., `claude-opus-4.6-no-tools-raw.md`)
  * **/API/**: API-specific prompts when different from web interface

  This helps track evolution over time while keeping the main directory clean.
</Accordion>

<Accordion title="Can I compare different versions over time?">
  Yes! Some interesting comparisons:

  **Claude Evolution**:

  * Compare `/Anthropic/old/claude-3.7-sonnet.md` with current `/Anthropic/claude-sonnet-4.6.md`
  * Notice how tool instructions became more sophisticated
  * Safety reminders expanded significantly

  **GPT Personality Variants**:

  * Compare all `/OpenAI/gpt-5.1-*.md` files
  * See how subtle changes create different tones
  * Learn techniques for personality engineering

  **Cross-Company Patterns**:

  * Compare Claude, GPT, and Gemini approaches
  * Notice common safety patterns
  * Identify unique innovations

  <Note>
    We're working on diff tools and visualization to make version comparison easier. Want to help? See [Contributing](/resources/contributing).
  </Note>
</Accordion>

## Contributing & Community

<Accordion title="How can I contribute?">
  Multiple ways to help:

  1. **Submit new prompts**: Extract and share new or updated system prompts
  2. **Improve documentation**: Fix typos, add analysis, write guides
  3. **Report issues**: Flag inaccuracies or outdated information
  4. **Build tools**: Create extraction scripts, diff tools, analyzers
  5. **Spread the word**: Share the collection with researchers and developers

  See our detailed [Contributing Guide](/resources/contributing) for instructions.
</Accordion>

<Accordion title="Who maintains this collection?">
  **Primary maintainer**: asgeirtj

  * GitHub: [asgeirtj](https://github.com/asgeirtj)
  * Discord: asgeirtj

  **Community**: This is a community-driven project. Major contributors are recognized in the repository.

  <Info>
    Want to become a maintainer? Regular, high-quality contributions may lead to maintainer access. Reach out on Discord!
  </Info>
</Accordion>

<Accordion title="Can I use this for commercial purposes?">
  **It depends**:

  ✅ **Generally OK**:

  * Learning techniques to improve your own prompts
  * Training your team on prompt engineering
  * Building tools that analyze or compare prompts
  * Research and development

  ❌ **Not OK**:

  * Directly copying prompts into commercial products
  * Claiming proprietary content as your own
  * Violating any applicable copyrights
  * Using in ways that violate provider terms of service

  <Warning>
    Consult with a lawyer if you're unsure about your specific use case. This FAQ is not legal advice.
  </Warning>
</Accordion>

<Accordion title="How can I get help or ask more questions?">
  Multiple channels:

  1. **GitHub Issues**: [Open an issue](https://github.com/asgeirtj/system_prompts_leaks/issues) for bugs, questions, or feature requests
  2. **Discord**: Message **asgeirtj** directly for prompt extraction help or contribution questions
  3. **Pull Requests**: Submit improvements and discuss in PR comments
  4. **Documentation**: Check our other resource pages:
     * [Prompt Engineering](/resources/prompt-engineering)
     * [Prompt Injection](/resources/prompt-injection)
     * [Contributing](/resources/contributing)
</Accordion>

## Ethical & Security Questions

<Accordion title="Is extracting system prompts harmful?">
  **It's complicated**:

  **Arguments for transparency**:

  * Users should know what instructions AI follows
  * Researchers need access to study AI behavior
  * Prompt engineering knowledge benefits everyone
  * Security through obscurity doesn't work long-term

  **Arguments for privacy**:

  * Companies invest heavily in prompt engineering
  * Public prompts make jailbreaking easier
  * May reveal competitive advantages
  * Could enable malicious replication

  <Info>
    This collection takes the stance that **education and transparency outweigh the risks**. However, we encourage responsible use and disclosure practices.
  </Info>
</Accordion>

<Accordion title="Could this help attackers?">
  **Yes**, but:

  1. **Knowledge is already public**: These prompts are widely shared in AI communities
  2. **Defense through obscurity fails**: Attackers will find prompts regardless
  3. **Education helps defenders**: More people understanding prompt injection improves defenses
  4. **Responsible disclosure**: We follow ethical guidelines (see [Prompt Injection](/resources/prompt-injection))

  The security community consensus is that **responsible disclosure of vulnerabilities (including prompt extraction) ultimately makes systems safer**.
</Accordion>

<Accordion title="What do AI companies think about this?">
  Companies typically don't comment officially, but:

  * **Anthropic**: Has not requested takedowns, but builds prompt extraction defenses
  * **OpenAI**: Regularly updates prompts (suggesting they know about extraction)
  * **Google**: Similarly quiet but continues improving Gemini prompts

  No major company has:

  * Issued DMCA takedowns for this collection
  * Publicly condemned prompt extraction research
  * Successfully prevented all prompt extraction

  This suggests companies accept that **system prompts will be extracted** and focus on building robust systems rather than relying on secrecy.
</Accordion>

<Accordion title="What are the future implications?">
  As AI systems become more sophisticated:

  **Likely trends**:

  * Prompts will become longer and more complex
  * Multi-layered safety systems (prompts + separate filters)
  * Dynamic prompts that adapt to user behavior
  * Better extraction defenses (but never perfect)
  * More open-source models with public prompts

  **Questions for the future**:

  * Should system prompts be public by default?
  * Will regulations require prompt transparency?
  * How do we balance security and openness?
  * Can we build AI systems that don't rely on secret prompts?

  <Note>
    This collection will continue to document these developments as AI systems evolve.
  </Note>
</Accordion>

## Still Have Questions?

<CardGroup cols={2}>
  <Card title="Prompt Engineering" icon="wand-magic-sparkles" href="/resources/prompt-engineering">
    Learn techniques from professional prompts
  </Card>

  <Card title="Prompt Injection" icon="shield-halved" href="/resources/prompt-injection">
    Understand extraction methods and security
  </Card>

  <Card title="Contributing" icon="code-pull-request" href="/resources/contributing">
    Add to the collection or improve docs
  </Card>

  <Card title="GitHub" icon="github" href="https://github.com/asgeirtj/system_prompts_leaks">
    Visit the source repository
  </Card>
</CardGroup>

<Info>
  **Didn't find your answer?**

  Open an issue on [GitHub](https://github.com/asgeirtj/system_prompts_leaks/issues) or reach out to **asgeirtj** on Discord.
</Info>