0xeb
Then with C++ implementation, you get more portability than Python or other interpreted languages.
I also ported the Claude Agent SDK to C++, so fastmcpp is needed for that: https://github.com/0xeb/claude-agent-sdk-cpp
RapidJSON is a good suggestion, maybe I will switch to it at one point.
Fastmcpp (Fastmcp for C++)
A tale of reverse engineering 1001 GPTs: the good, the bad and the ugly
Last year, I spent 5 months reverse engineering custom GPTs from OpenAI.
In this video, I share all the learnings from: prompt engineering, injection, leaks, plagiarism, protection prompts, shady practices and more.
- Repo: https://github.com/0xeb/TheBigPromptLibrary - Video: https://youtu.be/5TFn13QOpU4
LLM devs and prompt engineers, you’ll find this research fun and informative!
A Tale of Reverse Engineering 1001 GPTs: The good, the bad And the ugly
Contributors welcome!
TheBigPromptLibrary
- https://github.com/0xeb/pyhiew/tree/main/bin/pyhiew - https://github.com/0xeb/pyhiew/tree/main/bin/pyhiew - https://0xeb.wordpress.com/2010/08/21/introducing-pyhiew/
Custom GPTs or the new Pirate Bay? A new security nightmare
I have been surveying hundreds of GPTs through my research for the GPT-Analyst GPT and the prompt protection instructions library (see my previous posts).What I found is a huge number of custom GPTs upload pirated PDFs and ebooks. For example: https://x.com/TechWithElias/status/1733448828542722102?s=20Additionally, I found an unbelievable level of sloppiness with some of the knowledge files...
I also made a comprehensive video discussing these protections: https://youtu.be/O8h_j9jJFjA
DISCLAIMER: nothing is fool proof