Impactful research. At scale.

Apart Research is a non-profit AI safety lab. We host open-to-all research sprints, publish papers, and incubate talented researchers to make AI safe and beneficial for humanity.

With partners and co-authors from world-class organizations

Recent news

Apart > News

AI Safety Entrepreneurship Hackathon Round-Up

In his Hackathon Round-Up we check out the winners of our AI Entrepreneurship Hackathon.

By 
Connor Axiotes
 on 
January 28, 2025
Apart > Research

Rethinking CyberSecEval: An LLM-Aided Approach to Evaluation Critique

Apart Research's newest paper Rethinking CyberSecEval: An LLM-Aided Approach to Evaluation Critique looks at LLM-assisted benchmark analysis.

Published research

We produce foundational research enabling the safe and beneficial development of advanced AI.

Google Scholar

Rethinking CyberSecEval: An LLM-Aided Approach to Evaluation Critique

Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities

Jacob Haimes*¹, Cenny Wenner*¹, Kunvar Thaman¹, Vassil Tashev¹, Clement Neo¹, Esben Kran¹, Jason Schreiber¹

¹Apart Research, *Lead Authors

Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts

Luke Marks∗†, Amir Abdullah∗† ♢, Clement Neo†, Rauno Arike†, David Krueger□, Philip Torr‡, Fazl Barez∗‡

†Apart Research, ♢Cynch.ai, □University of Cambridge, ‡Department of Engineering Sciences, University of Oxford

Interpreting Learned Feedback Patterns in Large Language Models

See all publications

Alex Foote*, Neel Nanda, Esben Kran, Ionnis Konstas, Shay Cohen, Fazl Barez*

RTML workshop at ICLR 2023
[Read Publication}

Neuron to Graph: Interpreting Language Model Neurons at Scale

Philip Quirke, Fazl Barez

arXiv
[Read Publication}

Understanding Addition in Transformers

Albert Garde*, Esben Kran*, Fazl Barez

NeurIPS 2023 XAI in Action Workshop
[Read Publication}

DeepDecipher

Michael Lan, Fazl Barez

arXiv
[Read Publication}

Locating Cross-Task Sequence Continuation Circuits in Transformers

Luke Marks∗†, Amir Abdullah∗† ♢, Clement Neo†, Rauno Arike†, David Krueger□, Philip Torr‡, Fazl Barez∗‡

†Apart Research, ♢Cynch.ai, □University of Cambridge, ‡Department of Engineering Sciences, University of Oxford

arXiv
[Read Publication}

Interpreting Learned Feedback Patterns in Large Language Models

Clement Neo*, Shay B. Cohen, Fazl Barez*

arXiv
[Read Publication}

Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions

[Read Publication}

Neuroplasticity in LLMs

Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark

ACL 2023
[Read Publication}

Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts

Jacob Haimes*¹, Cenny Wenner*¹, Kunvar Thaman¹, Vassil Tashev¹, Clement Neo¹, Esben Kran¹, Jason Schreiber¹

¹Apart Research, *Lead Authors

arXiv
[Read Publication}

Sleeper Agents

Evan Hubinger et al.

Anthropic
[Read Publication}

Events

Join experts and fellow researchers as we build AI safety together.

Women in AI Safety Hackathon

This event concluded on
Mar 10, 2025
with
entries from
signups
Join us for the Women in AI Safety Hackathon during International Women's Day weekend! This unique event brings together diverse perspectives to tackle crucial challenges in AI alignment, governance, and safety. Work alongside leading experts, develop innovative solutions, and help shape the future of responsible AI development. Open to all skill levels and backgrounds
Mar 7
to
Mar 10, 2025
7
Mar
7
Mar
7
Mar

Daedalus AI Safety Hacks

Independently organized SprintX
Virtual
7
Mar
Canceled

Daedalus AI Safety Hacks

Daedalus AI Safety Hacks

Independently organized SprintX
Virtual
7
Mar
7
Mar
7
Mar

Women in AI Safety Hackathon

Independently organized SprintX
🌏 Building the Future
7
Mar
Canceled

Women in AI Safety Hackathon

Women in AI Safety Hackathon

Independently organized SprintX
🌏 Building the Future
14
Mar
14
Mar
14
Mar

Hardware Challenge: Verify & Protect AI Hardware

Independently organized SprintX
🌏 Building the Future
In-person & Virtual
14
Mar
Canceled

Hardware Challenge: Verify & Protect AI Hardware

Hardware Challenge: Verify & Protect AI Hardware

Independently organized SprintX
🌏 Building the Future
In-person & Virtual

Apart Research

Get involved

Check out the list below for ways you can interact or research with Apart!

Let's have a meeting!

You can book a meeting here and we can talk about anything between the clouds and the dirt. We're looking forward to meeting you.

I would love to mentor research ideas

We have a design where ideas are validated by experts on the website. If you would like to be one of these experts, write to us here. It can be a huge help for the community!

Get updated on A*PART's work

Blog & Mailing list

The blog contains the public outreach for A*PART. Sign up for the mailing list below to get future updates.

People

Members

Central committee board

Associate Kranc
Head of Research Department
Commanding Center Management Executive

Partner Associate Juhasz
Head of Global Research
Commanding Cross-Cultural Research Executive

Associate Soha
Commanding Research Executive
Manager of Experimental Design

Partner Associate Lækra
Head of Climate Research Associations
Research Equality- and Diversity Manager

Partner Associate Hvithammar
Honorary Fellow of Data Science and AI
P0rM Deep Fake Expert

Partner Associate Waade
Head of Free Energy Principle Modelling
London Subsidiary Manager

Partner Associate Dankvid
Partner Snus Executive
Bodily Contamination Manager

Partner Associate Nips
Head of Graphics Department
Cake Coding Expert

Honorary members

Associate Professor Formula T.
Honorary Associate Fellow of Research Ethics and Linguistics
Optimal Science Prediction Analyst

Alumni

Partner Associate A.L.T.
Commander of the Internally Restricted CINeMa Research
Keeper of Secrets and Manager of the Internal REC

Newsletter

Stay updated with Apart

Follow the weekly updated from the Apart community and stay updated on the latest news, research, and events.