Applications close end of the day anywhere on Earth, 21st November, 2025.
We’re excited to be running our third iteration of ARBOx (Alignment Research Bootcamp Oxford), a 2-week intensive designed to rapidly build skills in ML safety!
ARBOx3 is an in-person, full-time program, based on the ARENA curriculum, running from 5th to 16th January 2026. We have run two successful ARBOx’s previously, and are excited to re-open this opportunity for another promising cohort of motivated individuals. ARENA and ARBOx alumni have gone on to become MATS scholars, LASR participants, AI safety engineers at organisations like Apollo Research, Anthropic, METR, and OpenAI, and even founders of their own AI safety initiatives.
During the programme, you’ll follow a compressed version of the ARENA syllabus. build gpt-2-small from scratch, learn interpretability techniques, understand RLHF, and replicate a paper or two. There will be lectures in the morning covering aspects of the syllabus, and afternoon pair-programming with TA support. During lunch break, there will be short talks from experts in the field, and we will host socials in the evenings. By the end, you’ll have hands-on experience with ML and safety techniques, a concrete mini project, and clear next steps for contributing to AI safety.”
We can provide accommodation support to non-Oxford residents, daily lunches, and potential travel support.
Programme Details
We provide Central Oxford accommodation for non-Oxford residents, lunch, and potential support with travel expenses.
Who should apply?
We’re looking for applicants with basic familiarity with linear algebra, Python programming, and AI safety is expected (e.g., having completed AI Safety Fundamentals or another fellowship).
You do not need to be an Oxford student to participate. ARBOx is designed to upskill participants in ML safety, targeting those who would benefit from this training, regardless of their background.
We think you would be a good fit if you are a postgraduate student or a working professional, though we will also consider strong undergraduate applicants.
Syllabus
We’ll cover:
building gpt-2-small from scratch
attention
replicating a paper or two (e.g. Redwood’s IOI paper)
and a brief introduction to RL and RLHF.
We’ll have lectures in the morning covering aspects of the syllabus, and the rest of the day will be spent pair-programming. During lunch break there will be short talks from experts in the field, and we plan to run a couple of socials for the participants.
Please share this with others in your network who you think might be interested - applications are open to all! If you have someone in mind, feel free to mention them in our referral form.
