Apart Research combines technical AI safety research with open research sprints and fellowships, helping researchers develop and test approaches to reducing AI risk.
Products & media
Open research events where participants collaborate on focused AI safety questions and develop technical projects with expert guidance.
Research fellowships where participants work on projects proposed by partner organizations with mentorship from researchers in the field.
A mentored research program that develops promising sprint projects into publishable AI safety research through Studio and Fellowship stages.
An evaluation benchmark that tests language models for manipulative dark patterns, using prompts designed to reveal problematic behavior.
A research platform connecting open AI safety questions with expert review, researcher contributions, and funding pledges.
Cosigns
“Collaborating with Apart for the Code Red Hackathon has been useful to METR’s work on developing a set of evaluation tasks. While our main priority was to receive high-quality task implementations, the hackathon was also a great chance to engage with the research community, improve our documentation, and spread awareness about our ongoing task bounty.”
“The Hackathon was a clear success for us at the Cooperative AI Foundation. We saw participants from all over the world bring fresh perspectives, which helped us create an inclusive and intellectually diverse environment.”
Team
Founders
1 person
