hackertube.io

Multi-Agent Hide and Seek

OpenAI · demo · Watch on YouTube

Machine learning & deep learningAI safety, AGI & impact

What it is

OpenAI's short demo of agents playing hide-and-seek in a simulated environment. Through self-play, the agents develop six progressively more complex strategies and counter-strategies, including tool use.

Why Hacker News recommends it

HN uses it as a vivid example of emergent behavior from multi-agent reinforcement learning, and as a way to make AI misalignment concerns feel concrete.

  • 1 people recommended it
  • 1 different months
  • 0 strong recommendations
  • first 2019, last 2024

What HN commenters said

  1. “This short video makes the concern much more real”

    Short video making AI misalignment concerns feel real

    aeternum, 2019-10 · Recommendation · in “Experts who say we shouldn't worry about superintelligent AI are wrong?”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: emergent behavior, self-play, openai, reinforcement learning, ai safety

Also recommended by the same people