HackerTube.dev

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

Two Minute Papers · 11M views · 2019-10-22 · 6:02

Open on YouTube ↗

If playback is restricted in your region, try opening the original video. Use Mark watched to add it to your marked videos.

Overview

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.

On Hacker News

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

Recommended by 2 HN people across 2 months · HN mentions 2020–2021

Topics

Machine learning & deep learning
Search by tags
openaihide and seekemergent behaviorreinforcement learningtwo minute papers

What people said

SatvikBeri · 2021-02 · Recommendation

Two minute papers has many fun examples of AIs with unexpected behavior, OpenAI's hide and seek is one of my favorites: [VIDEO]

Read the original HN comment ↗
sendbitcoins · 2020-05 · Recommendation

"Two Minute Papers" [VIDEO] GTC 2020 Part 2 was pretty good [LINK] Mostly I'm in a rut as well

Read the original HN comment ↗
montenegrohugo · 2021-03 · Reference

One of the problems we have to be conscious about with self supervised learning is that the already existing problem of transparency and understandability gets worsened by orders of magnitude. If current billion parameter models are opaque, the result of SSL is, or will be, the equivalent of a black hole. How do you understand what the model has learned? Why has it learned that way? What things could have possible gone completely, horribly wrong in its quest to optimize its loss function? This somewhat humorous but also worrying paper comes to mind: [VIDEO] I think we really need to consider how we can mitigate the risk of raising completely ununderstandable yet scarily capable machines.

Read the original HN comment ↗

Sources

Video by Two Minute Papers, played through YouTube.

Data and selection notes

HN summaries and labels may contain AI errors. HN dates refer to discussions, not video publication.

HN Library: HackerTube export (2026-10-31) and open-index/hacker-news. Upstream summaries and classifications may contain AI errors.

Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.

Selection checks
  • SaaS & AI candidates: Topic keywords do not match
  • Editor-approved picks: Editorial review is required

Rule matches identify candidates. They do not guarantee video quality or financial results.

About the library and its sources