Skip to content
View dr-gareth-roberts's full-sized avatar
37 followers · 92 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLOAchievement: Quickdraw

Highlights

  • Pro

Block or report dr-gareth-roberts

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
dr-gareth-roberts/README.md

Dr. Gareth Roberts

Bridging how brains think and machines learn

LinkedIn Google Scholar Blog Email

Current Work

insideLLMs

insideLLMs is a Python library and CLI for comparing LLM behaviour across models using shared probes and datasets. The harness is deterministic by design, so you can store run artefacts and reliably diff behaviour in CI.

adversarial-debate

Multi‑agent AI security testing framework that orchestrates red‑team analyses, consolidates findings with an arbiter, and records an immutable audit ledger—plus a deterministic demo mode for repeatable results.

Background

PhD in Cognitive Neuroscience & AI · 15+ years in human-centred AI · 14 publications · h-index 12

Culture Amp · NEOS Insurance · Source Localisation · University of Sydney

Stack

Python PyTorch LangChain HuggingFace R TypeScript

Pinned Loading

  1. insideLLMs insideLLMs Public

    insideLLMs is a Python library and CLI for comparing LLM behaviour across models using shared probes and datasets. The harness is deterministic by design, so you can store run artefacts and reliabl…

    Python 1

  2. adversarial-debate adversarial-debate Public

    Multi‑agent AI security testing framework that orchestrates red‑team analyses, consolidates findings with an arbiter, and records an immutable audit ledger—plus a deterministic demo mode for repeat…

    Python

  3. Powerful-Prompts Powerful-Prompts Public template

    Deep dives on a single keyword? Impressive Fermi estimations? Struggling to handle word math problems? Solutions are all here.

  4. anthropics/claude-cookbooks anthropics/claude-cookbooks Public

    A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

    Jupyter Notebook 32.6k 3.4k