Singapore Technical Alignment Research Accelerator (STARA)
The first Singapore-based AI Safety bootcamp to accelerate careers in research engineering
​
Dates: Tentatively June 2–30
Venue: Singapore AI Safety Hub (22 Cross Street)
​​​​
About STARA
STARA (Singapore Technical Alignment Research Accelerator) is a Singapore-based AI Safety Bootcamp based on the global ARENA program — a hands-on, fast-paced accelerator that’s launched people into OpenAI, Anthropic, and top safety research fellowships like MATS.
Curriculum
Week 1
Fundamentals
In this week, you’ll learn about some coding best practices, become familiar with the PyTorch library, and build & train your own neural networks (CNNs and ResNets).
Week 2
Transformers and Mechanistic Interpretability
The transformer is an important neural network architecture used for language modelling, and it has made headlines with the introduction of models like ChatGPT.
​
In this week, you will learn all about transformers, and build and train your own. You’ll also learn about Mechanistic Interpretability of transformers, a field which has been advanced by Anthropic’s transformer circuits sequence and work by Neel Nanda.
Week 3
LLM Evaluations
In this week, you’ll learn how to evaluate LLMs. We’ll take you through the process of building a multiple-choice benchmark from scratch and using this to evaluate current models.
​
We’ll then move on to study LM agents: how to build them, and how to evaluate them.
Week 4
Capstone Project
In this week, you will work on a capstone project.
You’ll have the chance to dig into a topic that you found interesting during the course, applying the skills and knowledge you’ve accumulated over the last four weeks.