AI Safety

A*PART Research

Apart Research is an independent research organization focusing on AI safety. We facilitate and run hackathons and support individuals in technical AI safety research.

We host research sprints across the world

Updates on ours and others ML safety research

Discord iconGithub iconLinkedin iconYouTube iconMedium icon

A*PART Lab

Join a research program with likeminded people!

We collaborate on promising projects from talented individuals in the AI safety field. These often arise from our hackathons in e.g. interpretability. See the lab participants who are confirmed co-authors on accepted papers below.

Published work from the Apart Lab

N2G: A Scalable Approach for Quantifying Interpretable Neuron Representation in Large Language Models

Alex Foote1*, Neel Nanda2, Esben Kran1, Ionnis Konstas3, Fazl Barez1,3,4*

1Apart Research  2Independent  3Edinburgh Centre for Robotics  4University of Oxford
* Equal contribution

Read paperVisit project site

May 5, 2023  |  RTML workshop at ICLR 2023

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

Jason Hoelscher-Obermaier1*, Julia Persson1*, Esben Kran1, Ionnis Konstas2, Fazl Barez1,3*

1Apart Research 2Edinburgh Centre for Robotics 3Department of Engineering Sciences, University of Oxford
* Equal contribution

Visit project site

July 10, 2023  |  ACL 2023

Risks from artificial intelligence

Why AI Safety?

AI is advancing rapidly, and it won't be long before they surpass humans in various domains. As this technological progress continues, it is crucial that we prioritize the safety of these systems. Without proper safeguards in place, we expose ourselves to existing  risks.

A*PART is committed to supporting researchers in the field of ML safety. Our goal is to foster a deeper understanding of AI and how to make it safer.

If you would like to invite us to speak at your event, please contact us at operations@apartresearch.com.

Stay informed and join the discussion - together, we can shape the future of AI and ensure its safe and responsible development.

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