Newshot

ARENA 10.0: Call for Applicants

Summary

TL;DR: We are excited to announce the tenth iteration of ARENA (Alignment Research Engineer Accelerator), a 4-5 week ML bootcamp with a focus on AI safety! ARENA’s mission is to provide talented individuals with the skills, tools, and environment necessary for upskilling in ML engineering, for the purpose of contributing directly to AI alignment in technical roles. ARENA 10.0 will be running in-person from LISA from Mar 1st – Apr 2nd, 2027 (the first week is an optional review of the fundamentals of neural networks). Apply here to participate in ARENA 10.0 before 11:59pm (anywhere on Earth) on Sunday December 6th, 2026! Summary: ARENA has been successfully run nine times, with alumni going on to become MATS scholars and LASR participants, AI safety engineers at Apollo Research , Anthropic , METR , and even starting their own AI safety organisations ! This iteration will run from Mar 1st – Apr 2nd, 2027 (the first week is an optional review of the fundamentals of neural networks) at the…

Original text(via LessWrong)
arena_logo
arena_logo

TL;DR:

We are excited to announce the tenth iteration of ARENA (Alignment Research Engineer Accelerator), a 4-5 week ML bootcamp with a focus on AI safety! ARENA’s mission is to provide talented individuals with the skills, tools, and environment necessary for upskilling in ML engineering, for the purpose of contributing directly to AI alignment in technical roles. ARENA 10.0 will be running in-person from LISA from Mar 1st – Apr 2nd, 2027 (the first week is an optional review of the fundamentals of neural networks).

Apply here to participate in ARENA 10.0 before 11:59pm (anywhere on Earth) on Sunday December 6th, 2026!

Summary:

ARENA has been successfully run nine times, with alumni going on to become MATS scholars and LASR participants, AI safety engineers at Apollo Research, Anthropic, METR, and even starting their own AI safety organisations!

This iteration will run from Mar 1st – Apr 2nd, 2027 (the first week is an optional review of the fundamentals of neural networks) at the London Initiative for Safe AI (LISA) in Shoreditch, London. LISA houses AI safety organisations (e.g., Apollo Research, BlueDot Impact, IAPS), several other AI safety researcher development programmes (e.g., LASR Labs, MATS extension, Pivotal), and many individual researchers (independent and externally affiliated).

Being situated at LISA therefore brings several benefits, e.g., facilitating discussions about AI safety and different agendas, allowing participants to form a better picture of what working on AI safety can look like in practice, and offering chances for research collaborations post-ARENA.

The main goals of ARENA are to:

  • Help participants upskill in ML relevant for AI alignment.
  • Produce researchers and engineers who want to work in alignment, and help them make concrete next career steps.
  • Help participants develop inside views about AI safety, and the paths to impact of different agendas.

The structure of the programme will remain broadly the same as ARENA 9.0. For more details, see our website.Also, please note that we have a Slack group designed to support the independent study of the material (join link here).

Outline of Content:

The 4-5 week programme will be structured as follows:

Week 0 (Optional): Deep Learning Fundamentals

Before getting into more advanced topics, we first cover the basics of deep learning, including basic machine learning terminology, what neural networks are, and how to train them. We will also cover some subjects we expect to be useful going forward, e.g. using Large Language Models to streamline your learning, good coding practices, and version control.

Note: Participants can optionally skip this week of the programme and join us at the start of week 1 if:

  • they’re unable to attend otherwise, and
  • we’re confident that they are already comfortable with the material in this week.

It is recommended that participants attend, even if they’re familiar with the fundamentals of deep learning.

Topics include:

  • PyTorch basics
  • CNNs, Residual Neural Networks
  • Optimisation (SGD, Adam, etc)
  • Backpropagation
  • Hyperparameter search with Weights and Biases

Week 1 - Transformers & Interpretability

This week, you will learn all about transformers and build and train your own. You'll also study LLM interpretability, a field which has been advanced by Anthropic’s Transformer Circuits Thread, and work by Neel Nanda and the Google DeepMind Interpretability Team. This week will also branch into areas more accurately classed as 'alignment science' than interpretability, for example, work on token-level analysis of reasoning models, and model organisms of misalignment.

Topics include:

  • GPT models (building your own GPT-2)
  • Training and sampling from transformers
  • TransformerLens
  • In-context Learning and Induction Heads
  • Indirect Object Identification
  • Steering Vectors
  • Linear Probes
  • Pragmatic Interpretability

Week 2 - Reinforcement Learning

This week, you will learn about some of the fundamentals of RL and work with Gymnasium to run your own experiments.

Topics include:

  • Fundamentals of RL
  • Vanilla Policy Gradient
  • Proximal Policy Optimisation
  • LoRA and GRPO

Week 3 - Model Evaluations

This week, you will learn how to evaluate models. We'll take you through the process of building a multiple-choice benchmark of your own and using this to evaluate current models through UK AISI's Inspect library. We'll then move on to study LM agents: how to build them and how to elicit behaviour from them. We'll also have the option for participants to explore beyond evals, and study some of the methods used in AI control.

Topics include:

  • Constructing benchmarks for models
  • Using models to develop safety evaluations
  • Building pipelines for model evaluation
  • Building and eliciting LM agents
  • Introduction to AI control
  • Evaluation case studies

Week 4 - Capstone Project

We will conclude this program with a Capstone Project, where participants will receive guidance and mentorship to undertake a 1-week research project building on materials taught in this course. This should draw on the skills and knowledge that participants have developed from previous weeks and our paper replication tutorials.

Here is some sample material from the course on how to replicate the Indirect Object Identification paper (from the week on Transformers & Interpretability). An example Capstone Project might be to apply this method to interpret other circuits, or to improve the method of path patching. You can see some examples of Capstone Projects from previous ARENA participants here, as well as posts on LessWrong here and here.

Call for Staff:

ARENA has been successful because we had some of the best in the field TA-ing with us and consulting with us on curriculum design. If you have particular expertise with topics in our curriculum and want to apply to be a TA, use this form to apply. TAs will be well compensated for their time. Please contact [email protected] with any further questions.

FAQs:

Q: Who is this programme suitable for?

A: There’s no single profile that we look for at ARENA; in recent iterations, successful applicants have come from diverse academic and professional backgrounds. We intend to keep it this way – this diversity makes our bootcamps a more enriching learning experience for all.

When assessing applications to our programme, we like to see:

  • Applicants who genuinely care about AI safety and making the future development of AI go well;
  • Applicants who are able to code well in Python, and have some knowledge of the maths needed for modern AI (linear algebra, calculus, probability);
  • A solid understanding of how you might best contribute to technical AI safety, and how you expect ARENA to help you achieve your goals.

Since ARENA is an ML bootcamp, some level of technical skill in maths and coding will be required – more detail on this can be found in our FAQs. However, if our work resonates with you, we encourage you to err on the side of applying.

Q: What will an average day in this programme look like?

A: At the start of the programme, most days will involve pair programming, working through structured exercises designed to cover all the essential material in a particular week. The purpose is to get you more familiar with the material in a hands-on way. There will also usually be a short selection of required readings designed to inform the coding exercises.

As we move through the course, some weeks will transition into more open-ended material. For example, in the Transformers and Interpretability week, after you complete the core exercises, you'll be able to choose from a large set of different exercises, covering topics as broad as model editing, superposition, circuit discovery, grokking, discovering latent knowledge, and more. In the last week, you'll choose a research paper related to the content we've covered so far & replicate its results (possibly even extend them!). There will still be TA supervision during these sections, but the goal is for you to develop your own research & implementation skills. Although we strongly encourage paper replication during this week, we would also be willing to support well-scoped projects if participants are excited about them.

Q: How many participants will there be?

A; We're expecting to accept around 40 participants in the in-person programme.

Q: Will there be prerequisite materials?

A: Yes, we will send you prerequisite reading & exercises covering material such as PyTorch, einops and some linear algebra a few weeks before the start of the programme. This should take about 8 hours to complete.

Q: When is the application deadline?

A: The deadline for submitting applications is 11:59pm Anywhere on Earth on Sunday December 6th, 2026.

Q: What will the application process look like?

A: There will be three steps:

  • Fill out the application form;
  • Perform a coding assessment;
  • Interview virtually with one of us, so we can find out more about your background and interests in this course.

Q: Can I join for some sections but not others?

A: Participants will be expected to attend the entire programme. The material is interconnected, so missing content would lead to a disjointed experience. We have limited space and, therefore, are more excited about offering spots to participants who can attend the entirety of the programme.

The exception to this is the first week, which participants can opt in or out of based on their level of prior experience (although attendance is strongly recommended if possible).

Q: Will you pay stipends to participants?

A: We won't pay stipends to participants. However, we will be providing housing, food and travel assistance to our participants (see below). We aim to ensure that finances do not present a barrier to any candidates participating in ARENA.

Q: Which costs will you be covering for the in-person programme?

A: We will cover all travel expenses to and from London (which will vary depending on where the participant is from) and expenses incurred in acquiring a travel visa, where needed. Accommodation, meals, and drinks and snacks will also all be included during the duration of the programme.

Q: I'm interested in trialling some of the material or recommending material to be added. Is there a way I can do this?

A: If either of these is the case, please feel free to reach out directly via an email to [email protected]. We'd love to hear from you!

Links to Apply:

Here is the link to apply as a participant. We expect it to take no more than 90 minutes.

Here is the link to apply as a TA. You shouldn't spend longer than 30 minutes on it.

We look forward to receiving your application!

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by LessWrong
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗