←Story detail

Trending story

Liu Feng's team proposes AI "Robinson Test"

1 reports1 story updatesUpdated Oct 30 22:28

Understand this story

AI overview

Dr. Liu Feng's research team has proposed an AI "Robinson Test," designed to examine whether, after the removal of continuous human maintenance and task instructions, an AI can sustain itself, proactively expand its living space, and whether it adopts a cooperative, adversarial, or neutral attitude toward humans. The test is based on the theory of generalized agents and stands in contrast to the Turing Test, which examines whether an AI "seems human"; it focuses instead on "whether it can survive without humans." The test is divided into a nurturing period, a handover period, and a letting-go period, with the letting-go period lasting up to one year, and disturbances such as power outages and hard drive failures are randomly injected; results are classified into levels zero through four.

AI-generated from public reports

Latest development · Report

Liu Feng's team proposes the "Robinson Test": Can AI survive on its own after humans are removed?

Developments

1 confirmed developments

  1. Liu Feng's team proposes AI "Robinson Test"

    Source:36Kr · AI

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Oct 30

  1. 36Kr · AI

    Liu Feng's team proposes the "Robinson Test": Can AI survive on its own after humans are removed?

    Dr. Liu Feng, author of "The Rising Superintelligence," and his research team have proposed the "Robinson Test," which observes whether AI can sustain itself, proactively expand its living space, and whether it is cooperative, adversarial, or neutral toward humans after continuous human maintenance and task instructions are withdrawn. The test is divided into a nurturing period, a handover period, and a letting-go period, with the letting-go period lasting up to one year, and disturbances such as power outages and hard drive failures are randomly injected; results are graded from level zero to level four. The concept is based on the theory of generalized agents and stands in contrast to the Turing Test, which examines whether AI "seems human," focusing instead on "whether it can survive without humans."

Related stories

  1. Related storiesAnthropic Releases Randomized Controlled Trial on Analysts' Deference to AI Agent Judgment
  2. Related storiesOpenAI unveils expanded multi-layered misalignment behavior monitoring system
  3. Related storiesFangcun submits DeepSeek V4.1 Flash-1017 safety evaluation report
  4. Related storiesEpoch AI releases study on GLM 5.3 exploiting Firefox patch window