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, multimodal experiments, and the tools I build along the way. My goal is simple: understand how AI systems fail, and help make them safer, more predictable, and more resilient.

If you’re interested in AI safety, red‑team work, or model robustness, you’re in the right place.