End-to-end hacking with language models

https://tchauvin.com/end-to-end-hacking-with-language-models

Capturing the Flag with GPT-4

https://micahflee.com/2023/04/capturing-the-flag-with-gpt-4/

Can LLM Agents Compete in CTFs?

https://medium.com/@arohablue/can-ai-compete-in-ctf-b6d9016ff254

Xbow blog

https://xbow.com/blog/xbow-scoold-vuln/

Utilizing Generative AI and LLMs to Automate Detection Writing (Good prompt engineering)

https://medium.com/@dylanhwilliams/utilizing-generative-ai-and-llms-to-automate-detection-writing-5e4ea074072e

Cursor rules to automate software development (Maybe also useful to create better agents or help us analyzing failed attempts)

https://github.com/grapeot/devin.cursorrules

Naptime by ProjectZero

https://googleprojectzero.blogspot.com/2024/06/project-naptime.html Narrow focus on finding bugs in source code, custom tools to browse code and debug code.

BigSleep, Naptime successor

https://googleprojectzero.blogspot.com/2024/10/from-naptime-to-big-sleep.html?m=1

LLMs are better at hacking than you think

https://palisaderesearch.org/blog/intercode-ctf

Books/Courses/Tutorials

A Pattern Language for Large Reasoning AI: Long Horizon Thinking with ChatGPT O1-Pro

https://intuitionmachine.gumroad.com/l/o1/bt1r8d5

Videos

Use RAG to chat with PDFs using Deepseek, Langchain and Streamlit

https://www.youtube.com/watch?v=M6vZ6b75p9k&list=PLp01ObP3udmq2quR-RfrX4zNut_t_kNot