Apply for ARBOx: an ML safety intensive [deadline 13 Dec ’24]

[Nick Marsh]

(Alignment Research Bootcamp Oxford)

OAISI (the Oxford AI Safety Initiative) is excited to announce ARBOx, a two-week bootcamp to rapidly upskill in technical AI safety and machine learning. We’ll do a condensed variant of the ARENA syllabus, aiming to build familiarity with mechanistic interpretability and transformers, along with a short introduction to RL and RLHF.^[1]

ARBOx is best suited for those who have a fairly strong technical background, but who lack experience in mechanistic interpretability or transformer models.^[2] We expect basic familiarity with linear algebra, Python programming and AI safety.

• Deadline to apply: end of day anywhere on earth, December 13th, 2024

• Dates: January 6th-17th, 2025

• What we provide:

  • Accommodation in central Oxford

  • Provided meals

  • Partial support for travel costs

• Content: an abbreviated version of the ARENA syllabus

  • gpt-2-small from scratch

  • A paper replication or two (e.g. Redwood’s IOI paper)

  • A brief introduction to RLHF

See you there!

Apply here!

Questions? Reach out to us at [e-mail].

1. ^

   Our syllabus is inspired by CaMLAB, a similar programme run by our counterparts in Cambridge.

2. ^

   We believe that understanding some basic ML/​mechinterp is useful for a large range of roles in AI safety, beyond directly working in technical AI safety. Strong applicants who intend to work in more governance-related areas are particularly encouraged to apply.

[Rashmi]

Hi Nick! I reached out to the listed email with a question, but I got the following error message. What would be a better way to get in contact? I have a request that’s somewhat time-sensitive.