CognitiveCoefficient
Detail
Join free
Overview / Rankings / AI Minds 500 / Tom Lieberum

Tom Lieberum

All AI minds
AI advancement report · generated from Tom Lieberum's indicators

Tom Lieberum, full AI read

Tom Lieberum, Research Engineer, Google DeepMind, Google DeepMind (United Kingdom), ranks #424/520 on the AI Advancement Index (63.7). Known for Mechanistic interpretability research on DeepMind's team; sparse autoencoders at scale (Gemma Scope) and circuit-level analysis of transformer behavior.

Role
Research Engineer, Google DeepMind
Affiliation
Google DeepMind
Country
United Kingdom
Field
AI safety & alignment
Known for
Mechanistic interpretability research on DeepMind's team; sparse autoencoders at scale (Gemma Scope) and circuit-level analysis of transformer behavior

Dimension read

DimensionValueStandingWhat a high vs low value means, and where Tom Lieberum sits
AAI AI Advancement (AAI)63.7Developing · #423/520Low here, lower relative influence within this elite set.
▲ high: among the very top minds advancing AI  ·  ▼ low: lower relative influence within this elite set
Research influence Research influence58.0Developing · #439/520Low here, limited direct research influence.
▲ high: field-defining research contributions  ·  ▼ low: limited direct research influence
Frontier role Frontier role70.0Moderate · #223/520Mid-pack. High would mean central to building today's frontier AI; low would mean removed from frontier development.
▲ high: central to building today's frontier AI  ·  ▼ low: removed from frontier development
Thought leadership Thought leadership56.0Developing · #423/520Low here, limited public/field influence.
▲ high: shapes how the field and public think about AI  ·  ▼ low: limited public/field influence
Field-building Field-building56.0Developing · #440/520Low here, limited field-building footprint.
▲ high: builds the field, mentorship, institutions, tools, community  ·  ▼ low: limited field-building footprint
Momentum Momentum78.0Moderate · #238/520Mid-pack. High would mean driving AI's advancement right now; low would mean less active at the current frontier.
▲ high: driving AI's advancement right now  ·  ▼ low: less active at the current frontier

Strengths

  • No standout dimension.

Risk factors

  • A significant, well-rounded contributor to AI's advancement.
These are model outputs and scenarios, not forecasts of actual outcomes. This platform measures access to, utilization of, and leverage from cognitive infrastructure, not intelligence. No causality or certainty is claimed.

AI worldview

Contingent / balancedconfidence 0.6

Ideas & positions

Tom Lieberum is a Research Engineer at Google DeepMind, focusing on AI safety and alignment, particularly through mechanistic interpretability research. He has contributed to significant projects such as sparse autoencoders at scale (Gemma Scope) and circuit-level analysis of transformer behavior. Lieberum emphasizes the importance of understanding and controlling the internal mechanisms of AI systems to ensure they behave as intended. While he has not made extensive public statements on existential risk, his work suggests a strong concern with ensuring AI systems are safe and aligned with human values. He has not taken a definitive public stance on open vs closed models or regulation, but his focus on interpretability implies a preference for transparency and accountability in AI development.

What shapes the view

Lieberum's views are shaped by his technical background in deep learning and his commitment to AI safety. His work at DeepMind, a leading institution in AI research, likely influences his emphasis on rigorous scientific methods and empirical validation. The practical challenges of ensuring AI systems are interpretable and controllable may also inform his cautious approach to AI deployment. His professional history in cutting-edge AI research suggests a pragmatic and technically grounded perspective on the potential and risks of AI.

The AI-powered future they see

Lieberum publicly predicts a future where AI systems are increasingly sophisticated and integrated into various aspects of society. He promotes the idea that through careful research and development, these systems can be made transparent and reliable, reducing the risk of unintended consequences. His work suggests a vision of AI that is both powerful and safe, with a focus on aligning AI goals with human values and ensuring that AI systems can be understood and controlled.

DystopianContingentUtopian
An AI-generated synthesis of the public record (statements, essays, interviews, papers), not statements by the person; positions evolve and the model's knowledge has a cutoff.