Open-Sourced Comprehensive Prompt Hacking Course: Jailbreaks and Red/Blue Teaming
tom_doerr · x · 2026-08-09
TrustAI Laboratory has open-sourced a comprehensive tutorial project called Learn-Prompt-Hacking on GitHub.
The course systematically outlines prompt engineering and LLM security attack/defense systems, mainly covering:
- Basics & Applications: Prompt engineering techniques and GenAI development
- Red Teaming: ChatGPT jailbreaks, GPTs prompt injection & leaks, adversarial machine learning
- Blue Teaming: LLM security defense technologies, inference reinforcement
- Resources: LLM security papers, conference slides, and testing benchmarks
More from coding & agent
- The Design Paradox of AI Memory: Why Not Let Models Extract Their Own Memories? — mertdumenci · 2026-08-09
- Prompt Injection Test: Most Capable Model Falls for Bait, Proving Architecture > Model — Dangerous_Bus4157 · 2026-08-09
- AllMCPs Launches: A Free MCP Server Discovery Platform Built for Agents — moxie-docs · 2026-08-09
- LLM Routers in Practice: 35% Lower Cost and +1.3% Better Quality — zainhas · 2026-08-09
- LifeOS: An Open-Source AI Harness for Guided Self-Optimization in Life and Work — tom_doerr · 2026-08-09
- 'Just One More Tool Bro': The Comedy of Stacking Tools in AI Agent Workflows — DavidWells · 2026-08-09