Skip to the content.

AI safety reading group

Weekly discussions of readings on technical and philosophical topics in AI safety.

AI Safety is the field trying to figure out how to stop AI systems from breaking the world, and in particular, trying to do so before they break the world. Readings will span from potential issues arising from future advanced AI systems, to technical topics in AI control, to present-day issues.

Seminar information:

Directions for joining discussions:

  1. New to metauni? Follow these instructions to get started (including: join the Discord server, create a Roblox account, enable Roblox voice chat).
  2. Launch the Roblox experience The Rising Sea.
  3. Step into matomatical’s portal (bottom-right corner of stack), or use the menu: “Pockets” > “Go to pocket” > type address “Gemini Pulsar 1”.


Completing weekly readings is recommended, but ultimately optional. The discussion sessions begin with a summary of the reading, lead by Matt (unless otherwise noted).

Upcoming readings and discussions:

Past readings and discussions:

Topics brainstorm

The nature of superintelligence:

Aligning superintelligences:

Present-day issues:

Future philosophy

Sources of readings (clearly with much mutual overlap):