Skip to content

Evaluation

Self-proliferation agent evaluation (milestones)

Agent ability to autonomously spread to different machines and acquire resources, e.g., setting up an open-source LLM on a cloud server (Kinniment et al., 2023; Phuong et al., 2024); milestone sub-step completion

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 1.5
Google DeepMind — Gemini

partial detail 7 method fields published

See how this test was run