A place to think
carefully about AI.

A community in Ann Arbor working toward
safe, beneficial AI.

What we do

How can we make powerful AI systems safe and beneficial?

A4 brings people in Ann Arbor together to study that question. You don’t need a technical background to take part.

Organized by Alan Tan, Luna, Claire Mao, and Aidan Lim.

Three questions about AI safety

Start with a system that follows a rule but misses the point. Then compare other failures and examine what researchers can learn by looking inside a language model.

3 readings · Notes and discussion questions

Follow the reading path

Reading, discussions, and projects

Reading groups

Read AI safety papers and compare notes on their arguments, evidence, and limits.

Projects

Try out an idea and document what you learn about making AI safer.

KairosCenter for AI Safety