Bridging how brains think and machines learn.
Python library and CLI for comparing LLM behaviour across models using shared probes and datasets. Deterministic by design—store artefacts and diff behaviour in CI.
Multi-agent AI security testing framework. Orchestrates red-team analyses, consolidates findings with an arbiter, and records an immutable audit ledger.
Step-by-step notebook on parameter-efficient fine-tuning of Google’s Gemma 2B using LoRA adapters with KerasNLP. Setup, training, and inference.