What Is AI Safety? A Field Map for Newcomers
AI Safety is not one problem but a family of them. Here is a map of the main research areas and how they connect.
Author
AI Safety is not one problem but a family of them. Here is a map of the main research areas and how they connect.
The two fields overlap, but they ask different questions. Confusing them makes both harder to do well.
Notes from our reading group on which of the paper’s five problems have become research fields — and which remain under-studied.
Most safety evaluations are written in English. What changes when we test in Sinhala, Tamil or Arabic?
A short introduction to how Sri Lanka’s data protection law applies to organisations building or deploying AI.
Every resource in the library shows who reviewed it and when. Here is what that review involves.
A reading order and a first experiment for engineers who want to understand what happens inside a model.
Practical questions to answer before giving a language-model agent access to tools, data or the internet.