AI safety & Security

Apart Research

Artificial intelligence will change the world. Our mission is to ensure this happens safely and to the benefit of everyone.

Join the AI Evaluation Tasks Bounty Hackathon with METR

Read
Apart > Research

Foundational Research for Safe and Beneficial Advanced AI

Apart > Sprints

Global Hackathons and Challenges in AI Safety for Aspiring Researchers

Apart > Lab

Incubating Talented Research Teams Towards Real-World Impact

With partners and collaborators from
Our Published Papers

Foundational AI Safety Research

We aim to produce foundational research enabling the safe and beneficial development of advanced AI. See our publications below.

Luke Marks, Amir Abdullah, Luna Mendez, Rauno Arike, Philip Torr, Fazl Barez

arXiv
[Read Publication}

Interpreting Reward Models in RLHF-Tuned Language Models Using Sparse Autoencoders

Alex Foote1*, Neel Nanda2, Esben Kran1, Ionnis Konstas3, Shay Cohen4, Fazl Barez1,4,5*

RTML workshop at ICLR 2023
[Read Publication}

Neuron to Graph: Interpreting Language Model Neurons at Scale

NeurIPS 2023 XAI in Action Workshop
[Read Publication}

DeepDecipher

Philip Quirke, Fazl Barez

arXiv
[Read Publication}

Understanding Addition in Transformers

Michael Lan, Fazl Barez

arXiv
[Read Publication}

Locating Cross-Task Sequence Continuation Circuits in Transformers

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

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

ACL 2023
[Read Publication}

The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python

Antonio Valerio Miceli-Barone1*, Fazl Barez1*, Ioannis Konstas2, Shay B. Cohen1

ACL 2023
[Read Publication}
No items found.

AI and Democracy Hackathon: Demonstrating the Risks

This event concluded on
May 6, 2024
with
entries from
signups
Join us to demonstrate the future of AI risk to democratic institutions with inspiring speakers and a worldwide community!
May 3
to
May 6, 2024
3
May

AI and Democracy Hackathon: Demonstrating the Risks

Virtual & Local
3
May
Canceled

AI and Democracy Hackathon: Demonstrating the Risks

AI and Democracy Hackathon: Demonstrating the Risks

Virtual & Local
24
May

AI Security Hackathon: Measuring AI Capability

Virtual & Local
24
May
Canceled

AI Security Hackathon: Measuring AI Capability

AI Security Hackathon: Measuring AI Capability

Virtual & Local
28
Jun

Deception Detection Hackathon: Can we prevent AGI from deceiving humans?

Virtual & Local
28
Jun
Canceled

Deception Detection Hackathon: Can we prevent AGI from deceiving humans?

Deception Detection Hackathon: Can we prevent AGI from deceiving humans?

Virtual & Local
What does Apart do?

We solve high-impact, neglected and tractable problems in AI safety

Field-building for AI safety

Our initiatives allow people from diverse backgrounds to have an impact on AI safety. On 7 continents, more than 200 projects have been developed by over 1,000 researchers. Some teams have gone on to publish their research at major academic venues, such as NeurIPS and ACL.

High-impact research

We engage in both original research and contracting for research projects that aim to translate academic insights into actionable strategies for mitigating catastrophic risks associated with AI. We have co-authored with researchers from the University of Oxford, DeepMind, Edinburgh University and more.

A vision for the future

Our aim is to foster a positive vision and an action-focused approach to AI safety, a commitment underscored by our signing of both the Statement on AI Risk and the Letter for an AI Moratorium. We are privileged to not only be tightly connected with but also actively develop a large community in AI safety.

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

Contact

Get in touch

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Apart Updates

Sign up for our updates

Follow the latest from the Apart Community and stay updated on our research and events.