hackertube.io

OpenAI Plays Hide and Seek…and Breaks The Game! 🤖

Two Minute Papers · explainer · Watch on YouTube

Machine learning & deep learning

What it is

Two Minute Papers covers OpenAI's multi-agent hide-and-seek experiment, in which agents learned emergent tool use and found ways to break the game's rules. It summarizes the 'Emergent Tool Use from Multi-Agent Interaction' paper.

Why Hacker News recommends it

HN mentions it as a fun and slightly worrying example of AI systems behaving in unintended ways when optimizing.

  • 2 people recommended it
  • 2 different months
  • 0 strong recommendations
  • first 2020, last 2021

What HN commenters said

  1. “Two Minute Papers"”

    Channel mention for browsing interesting AI papers.

    sendbitcoins, 2020-05 · Recommendation · in “Ask HN: What interesting stuff are you browsing?”

  2. “OpenAI's hide and seek is one of my favorites”

    Fun example of AI with unexpected behavior.

    SatvikBeri, 2021-02 · Recommendation · in “Medical chatbot using OpenAI’s GPT-3 told a fake patient to kill themselves”

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

Topics: openai, hide and seek, emergent behavior, reinforcement learning, two minute papers

Also recommended by the same people