A writing accelerator for AI safety
Applications close at 12pm
on Sunday 18 October.
The Alignment Desk is a structured writing programme for people in Cambridge or London who want to develop their thinking on AI safety and share it through published writing.
A small cohort meets on Saturdays at Meridian in Cambridge. You'll work on your own projects, with feedback from the group and weekly goals to help you finish them. We expect each participant to publish three pieces during term.
Now a Tarbell Fellow. He joined the programme as an MPhil student in Global Risk & Resilience at the Centre for the Study of Existential Risk. Previously a Technical Writer at Schneider Electric and Junior Researcher at the European Institute of Asian Studies. Bylines in East Asia Forum, EIAS and APEC features.
Masters in Mathematics from TU Munich and Bachelors from the University of Cambridge. Previously a quantitative trader in US Blue Chip ETFs, now pivoting into AI safety research through the ERA fellowship.
AI researcher with a PhD focused on AI security and adversarial robustness. Works on model failure modes, interpretability, and alignment, with a focus on how training objectives shape internal representations.
MPhil student in the Ethics of AI, Data and Algorithms at the University of Cambridge. Background in technology ethics and moral philosophy, with experience as an AI Analyst. Specialises in predictive AI, surveillance tech, fairness metrics, and AI governance.
Recent Mathematics Masters graduate, now upskilling in AI safety. Participated in ARBOx3 at the Oxford AI Safety Initiative.
2nd year Engineering student at Cambridge and Technical Officer at the Cambridge AI Builder Club. Background in full-stack software engineering, focused on bridging AI safety theory and engineering practice.
Third year undergrad engineer at Cambridge. Research interests include value alignment and how goal-directed behaviour emerges from RL. Helping out at CAISH since 2023, working on operations. Previously worked at Amazon doing software engineering, the Singapore AI Safety Institute researching hallucination detection, and a bit of singular learning theory.
2nd year Engineering student at Cambridge, currently exploring LLM finetuning and generalisation under a SPAR project. Interested in investigating technical solutions through a pragmatic lens through Alignment Desk. Background in robotics and software engineering.
Writing forces you to confront gaps in your understanding that remain hidden when you are just reading or thinking. It is also how people in this community come to know your work.
For many aspiring writers, the biggest challenge is turning ideas into finished pieces. Developing a habit of regular output is often what makes the difference between wanting to contribute and doing so.
"Writing is the single biggest difference-maker between reading a lot and efficiently developing real views on important topics."
Holden Karnofsky, Learning By Writing
We are flexible on format. What matters is that you have a concrete output in mind.
Review existing work on a technical or governance topic.
Explain a topic through an interactive piece or tutorial.
Steelman or red-team a research agenda.
Develop an argument, research note or proposal.
Present existing work for a new audience.
Write publicly about your career plans or uncertainties.
The application takes about 10 to 15 minutes. We ask about your background and for a sense of what you might write about.
Applications close at
Come to the apply-athon at Meridian on Saturday 17 October, 11am to 2pm, and work on your application alongside others.