Jack Hopkins Independent AI Safety Researcher

Projects

Factorio Learning Environment

Open-ended LLM agent benchmark built in Factorio

An open-source environment for evaluating LLM agents on complex, unbounded automation tasks with exponential complexity scaling.

NeurIPS 2025 935+ GitHub stars Open-source

Website GitHub Paper

Atlantic Row

40-day unsupported Atlantic crossing with a team of 4

Rowed 3,000 miles across the Atlantic Ocean in the 2018-19 Talisker Whisky Atlantic Challenge, finishing 5th and raising £25k for Multiple Sclerosis charities.

40 days at sea 5th place finish £25k raised for MS charities

Press

Lie Detection in LLMs

Do fine-tuned lie detectors generalise across domains?

Research investigating whether LLM-based lie detectors trained on one domain can detect deception in others, with implications for AI safety.

MATS/Anthropic fellowship Forthcoming 2026

HuggingFace

Overthinking

Amplifying reasoning weights to extract learned secrets

Using reasoning task vector arithmetic to amplify models' propensity to think out loud, surfacing hidden information up to 10× more frequently for pre-deployment safety auditing.

ICML 2026 submission Up to 10× improvement 2B-32B scale

Paper

Akkadian to English NMT

Neural machine translation of ancient cuneiform

Applying test-time compute to ancient language translation. Distilled reasoning chains from Claude Opus nearly double BLEU (63 vs 37) on Akkadian-to-English, filtering 140k ORACC lines down to 26k high-quality training pairs.

63 BLEU (val) 140k → 26k filtered pairs

HuggingFace