The Dwarkesh Reference
← Back
PredictionPending

A verifiable game like Go could be the outer-loop environment for training automated AI researchers, with skills transferring to harder domains.

Who
Eric Jang
Topic
Games as training loop
How it gets scored
Does a published agent improve a measurable AI metric through self-directed experiment selection using a game as the verification loop by end of 2028?
Resolves
2028-12-31