BLOG

Engineering write-ups on software, security and applied AI, including how we built Nemesis, our open-source fine-tuned offensive-security model.

How We Built Nemesis: an Open-Source Offensive-Security LLM

How we fine-tuned Qwen3.6-27B into Nemesis, an open-source LLM for authorised red-team work: 4-bit QLoRA, a refusal-filtered dataset, and honest evals.

Read article