Our Mission
To empower humanity by making breakthrough scientific progress on AI safety.
In order to make sure our research makes a difference, we engage with key stakeholders across government, industry, and academia.
We are building tools and resources to spread our research to the broader community.
Join the Discord Open RolesTo empower humanity by making breakthrough scientific progress on AI safety.
In order to make sure our research makes a difference, we engage with key stakeholders across government, industry, and academia.
Whether you're a mathematician or ML engineer, physicist or neuroscientist, learn the basics of SLT, developmental interpretability, and our broader agenda.
Want to start using SLT in your own research? Start here.
The Australian AI Safety Forum is a two-day interdisciplinary event scheduled for November 2024. This forum, the first of its kind in Australia, aims to discuss perspectives on technical AI safety and governance, and explore Australia’s unique role in the global AI safety landscape. The event will be anchored around the International Scientific Report on the Safety of Advanced AI, highlighting its key content and examining its implications for Australia.