https://pandaeatsbamboo.com/series/redteaming/Recent content in RedTeaming on PandaEatsBambooHugoenThu, 15 Oct 2026 11:27:29 +0530https://pandaeatsbamboo.com/posts/redteaming-1/Thu, 25 Dec 2025 00:00:00 +0000https://pandaeatsbamboo.com/posts/redteaming-1/This post shows how PyRIT’s executor enables practical multi-agent LLM red teaming by letting one model actively attack another. Using a local Ollama setup, I focus on the RedTeamingAttack flow, where attacker, target, and scorer models are orchestrated in a loop, with scoring and stopping logic handled entirely by the executor. The result is a reproducible, extensible way to automate jailbreak discovery without custom control logic, inspired by real-world AI-vs-AI and proxy-based PyRIT usage.