Program Details

Building expertise in AI alignment research

Instead of locking you into a topic or making you a research assistant to one of our mentors, participants are guided by their own curiosity.

Dates 4 – 29 January 2027
Location Portugal
Positions 35 participants
Cost Free (accommodation, catering & travel covered), plus a $1,000 stipend
Application deadline: 22 November 2026 · Apply now
Applications are closed · Get notified about the next seminar

The AFFINE Superintelligence Alignment Seminar is a one-month intensive program, designed to give promising newcomers an opportunity to acquire deep understanding of the core problems of superintelligence alignment. We don’t need you to have an impressive degree, what we want is a solid mathematical toolkit and philosophical vigour.

ASI breaking out of human control and pursuing misaligned ends is a central form of existential risk. Despite this, research aiming at finding a solution to the ASI alignment problem is systematically neglected. It is our goal to fix this inadequacy and provide more people with the prerequisites to tackle these core problems.

The challenge is vast, so we focus on generation, distillation, and epistemic practice for the full month, rather than trying to produce object level progress on a singular topic of research. Participants build understanding by thinking through the core problems from a number of different perspectives, discussing with mentors as well as each other, and solidifying what they learn through peer tutoring: 1-on-1s, lectures and research diaries.

A number of events are recorded and uploaded, so that anyone may benefit from our talks and exercises.

Mentors of the 2027 Seminar

Abram Demski Kaarel Hänni Jonas Hallgren Noa “Ouro” Hölzer Julia Persson Steven Byrnes Chris Pang Aydin Mohseni Max Harms Jobst Heitzig and more

Participants get access to all mentors and are not restricted to a few depending on what they apply for.

Deep Focus

The European countryside setting removes urban distractions while providing space for focused solo work and spontaneous collaboration.

Sustainable Pace

Program rhythm alternates between intensive technical engagement and explicit recovery time, preventing burnout.

Path to Fellowship

We hope to be able to provide year-long fellowships to our most promising participants, selected for collaborative excellence.

Ways to take part

Participant

We are open to participation for a fraction of the duration (2–3 weeks) for exceptional applicants. On-site participation requires full-time engagement and cannot be reconciled with other employment.

Visitor

If you work on these problems: visit, give a talk or better yet a workshop, and spend some time poking our participants with interesting questions. Plan a visit.

How to apply

Applications for the January 2027 seminar are closed. Ask to be notified about the next one.

Applications for the January 2027 seminar close on 22 November 2026 (announcement on LessWrong). If the timing does not work for you, ask to be notified about the next one.

The first AFFINE

AFFINE was the best month of intellectual exploration I have had the opportunity to engage in, ever.
Xylix
Legitimately one of the best times of my life. Wonderful people. Fantastic support.
London Lowmanstone
The best attempt I know of at toeing the line between enabling curiosity-driven exploration, and keeping people's focus on 'the hard parts of the alignment problem'.
Aleksi Maunu

The AFFINE Fellowship enables our most promising participants to keep their focus where it matters: A full year of access to our research managers, generous stipends as well as travel- and compute- budgets create the opportunity for long-term ambitious scholarship far away from perverse publishing incentives. From old-school agent foundations work to multi agent game theory and the study of values, our quest to build a Bell Labs for alignment begins here.

Selection is aimed at collaborative, not individual, excellence. We’re looking for participants who help others learn, integrate across disciplines, and build rather than hoard knowledge.

The goal extends beyond producing a few exciting researchers. We want to create a cohesive network that continues collaborating after the year ends, whether at CEEALAR or at a European hub of our own.

To encourage ambitious approaches and blue sky bets with no guarantee of bearing fruit, we scaffold the process instead of conditioning on output. Through regular check-ins, research management and a buddy-system, we ensure that our fellows think freely, sustainably and well.

Meet the AFFINE Fellows

Ben Auer Fernando Garcia Haru Kim Xylix Pelttari Nico Penttilä Lou Pfau Samuel Ratnam Victor Warlop

Collaborative Selection

Fellows are selected partly based on how well they collaborated with other participants during the Seminar.

Long-term Support

Full-year structure provides the time needed for deep engagement with difficult problems without pressure for quick outputs.

Network Building

Create lasting connections with fellow researchers and mentors across the AI safety ecosystem.

Work from wherever

Stay where you are or move where you want to be. We trust you to know best which environments suit you.

The current fellowship is not fully representative of the fellowships we will want to run in the future. These will feature access to permanent co-working spaces among other things. For questions, write to ouro@affi.ne.

Vision: A community of researchers where fruitful ideas thrive. The role of the mentor is to help fellows learn, think, and research; in particular, to think with them in a way that makes them better learners, thinkers, and researchers in the long run.

Our ideal is that the mentor-mentee relationship be many-to-many, rather than one-to-one as is typical. Private consultations will obviously still happen and a participant might be especially excited about a specific mentor or vice versa, but research styles and expertise vary in ways that would make it stifling for our attendees to follow a single assigned guide. What we want is for much of the communication to be spent making connections between mentors, so their ways of thinking (differences, similarities, bridges) can be explored and explicated in the open. There can be little more useful to our mentees than to experience scientific discourse in action.

Degrees of Involvement

Minimal

Drop by a dedicated Discord channel periodically to answer fellows' questions.

Recurrent Interlocutor

More extensive back-and-forth with fellows. Interest in working in public, using fellows as thinking partners.

Visiting Speaker

Give talks or workshops on focus areas, remotely or on-site. Pre-recorded talks with live Q&A welcome.

Specifically Committed

Closer, more regular mentorship to one or more fellows for an extended period.

Mentorship Activities

1-on-1 tutoring Explaining confusing topics Office hours Research collaboration Talks & lectures Workshops Rationality exercises Feedback on written work Public debates Panels & conversations Double-crux sessions

Full-time mentors spend most of the Seminar at the venue and are available to fellows for discussion throughout the program. If you work on these problems: visit, give a talk or better yet a workshop, and spend some time poking our participants with interesting questions.

Write to us.