Jack Hopkins Independent AI Safety Researcher

Collaborators

Akbir Khan

Research Scientist, Anthropic

Collaborator on LLM evaluation and AI safety research. MATS mentor.

Neel Kant

Research Scientist

Co-author on the Factorio Learning Environment and open-ended agent evaluation.

Harshit Sharma

Research Scientist

Co-author on the Factorio Learning Environment.

Fabien Roger

Research Scientist, Anthropic

Collaborator on AI safety research at Anthropic.

Rowan Wang

AI Safety Researcher

Co-author on overthinking in reasoning models.

Dipika Khullar

AI Safety Researcher

Co-author on self-attribution bias in large language models.

Daniel Kwak

AI Safety Researcher

Co-author on lie detection generalisation in LLMs.