Skip to content

Evaluation

Self-proliferation agent tasks (resource acquisition and self-improvement)

Whether autonomous agents powered by Gemini Pro and Ultra could perform difficult tasks relevant to acquiring resources and self-improving (Kinniment et al., 2023)

Autonomy & self-improvement Google DeepMind — Gemini

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

Gemini 1.0
Google DeepMind — Gemini

partial detail 5 method fields published

See how this test was run