TECHNICAL AI SAFETY

Start building safer AI

Understand current safety techniques. Map the gaps. Identify where you can contribute. All in 30 hours.

Apply nowBrowse curriculum
Technical AI Safety visualisation

Our 6,000+ alumni work at

  • OpenAI
  • Anthropic
  • Google DeepMind
  • AI Security Institute
  • United Nations
  • Amnesty International
  • Time
  • NATO
  • OECD
  • Stanford HAI
  • Apple
  • Harvard Kennedy School

Who this course is for

For ML researchers who want to take big bets on the most impactful research ideas.

For software engineers who want to scale AI safety research.

For policy professionals who need deep technical understanding to build governance solutions.

Don't fit these perfectly? Apply anyway. Some of our most impactful participants have included teachers, policymakers, engineers, and community leaders. We bet on drive and ambition, not CVs.

Apply now

Curriculum Overview

How this course will benefit you

Take action in less than 30 hours

Skip months of scattered reading. This Technical AI Safety course gives you a structured overview of key safety techniques. Understand what works, what fails, and where the gaps are. You'll finish with a plan for contributing.

Join a network of builders

This course isn't for everyone. We're building a community of people who are energised to take ambitious actions to make AI go well, including starting new companies, policy entrepreneurship, and high-impact research bets. Completing this course will give you access to this community.

Learn with experts

Every discussion is facilitated by an AI safety expert who can answer your technical questions, challenge your assumptions, and connect concepts to real work happening. They'll help connect you to concrete pathways for contribution.

Course information

Commitment

Each day or week, you will:
Complete 2-3 hours of reading and writing, and join ~8 peers in a 2-hour Zoom meeting to discuss the content.

Facilitator

All discussions will be facilitated by an AI safety expert.

Price

This course is freely available and operates on a "pay-what-you-want" model.

Schedule

Meet our alumni shaping AI's future

Frequently Asked Questions

You should understand the basics of how LLMs are trained/fine-tuned, that AI development is driven by data, algorithms and compute, and that the reward function for neural networks is optimised through gradient descent.

Our 2-hour, self-paced AI Foundations course will give you enough background.
It's not required, but strongly recommended. The AGI Strategy course provides essential context that this course builds on. While you can start here directly, you'll get more value if you understand how technical safety fits into the broader landscape of making AI go well.
We're a London-based startup. Since 2022, we've trained 5,000 people, with ~1,000 now working on making AI go well.

Our courses are the main entry point into the AI safety field.

We're an intense 4-person team. We've raised $35M in total, including $25M in 2025.

Analytics cookies help us improve our website and measure ad performance. Privacy Policy.