0xeb

It is not about optimization but more just having a C++ library.

Then with C++ implementation, you get more portability than Python or other interpreted languages.

Yes :)

Hi, I made that port. Performance was not the goal. Just the C++ port mainly.

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.

Use the Clauge Agent SDK from 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!

The Big Prompt Library is a collection of system prompts, GPT instructions, GPT protection/security instructions and various learning material!

Contributors welcome!

thanks for the links! especially the spiritual successor of Cantor Dust ;p

If you like scripting, you can use my HEM extension to write more stuff in Python:

- 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/

Sorry, I am new to HN. It seems the link was truncated after submission. Here it is: https://github.com/0xeb/gpt-analyst/blob/master/protecting-g...

I have spent a whole weekend curating a list of protection instructions (nothing is fool proof) for GPTs. This list is compiled from studying hundreds of leaked GPTs.

I also made a comprehensive video discussing these protections: https://youtu.be/O8h_j9jJFjA

DISCLAIMER: nothing is fool proof