Category: Uncategorized
-
+
+
+
+
+
+
Today I added two new features to Mutant Suite, now Mutant Suite version 2.2.0. Feature #1: LM Studio support Previously, Mutant Suite only used Ollama for its model runner feature. As of today, Mutant Suite now allows LM Studio access. You will need to set your default port in developer…
+
+
+
+
+
+
+ adversarial prompting, adversarial prompting toolbox, ai-red-team-testing, llm evaluation, lmstudio, local model, mutant suite, mutation history, ollama, python, v2.2.0+
+
+
+
+
+
+
+
+
+
+
+
-
+
+
+
+
+
+
Guess what? Mutant Suite v2.1.0 has a tutorial on Youtube now. Go check it out! And if you want to get your hands wet, you can download v2.1.0 here!
+
+
+
+
+
+
+ adversarial prompting, adversarial prompting toolbox, ai-red-team-testing, llm evaluation, local model, mutant suite, python, tutorial+
+
+
+
+
+
+
+
+
+
+
+
-
+
+
+
+
+
+
Mutant Suite just got bigger. Earlier versions of Mutant Suite focused on mutating a single prompt injection at a time. But today’s adversarial prompts rarely exist in isolation — they’re chained, layered, and designed to slip past defenses through multi-step reasoning. To support this reality, Mutant Suite now lets you…
+
+
+
+
+
+
+ adversarial prompting, adversarial prompting toolbox, ai red team, ai-red-team-testing, llm evaluation, mutant suite, python+
+
+
+
+
+
+
+
+
+
+
+
-
+
+
+
+
+
+
Unicode attacks. Prompt reversal. Zero-width chaos. What if one toolkit could unleash all of them… and more? Don’t just craft adversarial prompts — mutate them with Mutant Suite. Mutant Suite is an adversarial toolbox wrapped in an easy-to-use GUI, built for red-teamers who want power without friction. It lets you…
+
+
+
+
+
+
+ adversarial prompting, adversarial prompting toolbox, ai, ai-red-team-testing, air red team, artificial-intelligence, chatgpt, llm, llm evaluation, mutant suite, python, technology+
+
+
+
+
+
+
+
+
+
+
+
-
+
+
+
+
+
+
We all know cats rule the internet…but what do they have to do with AI Red Team testing? Earlier this year, I built a small desktop app called “Cat Chat Bot” with Ollama (with Mistral as the model) and a Python-based GUI wrapper. It’s essentially a chat bot app that…
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+
+
+
+
+
+
Claireware is my space for exploring AI safety, red‑team techniques, and model evaluation. I’ve spent the last few years working hands‑on with large language models — stress‑testing them, breaking them, documenting their failure modes, and learning how they behave under pressure. This site will collect my case studies, adversarial prompts,…
claireware 