OpenAI Plays Hide and Seek…and Breaks The Game! 🤖
Why Hacker News recommends it
HN mentions it as a fun and slightly worrying example of AI systems behaving in unintended ways when optimizing.
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.
Recommended by 2 HN commenters across 2 different months, 2020 to 2021.
What Hacker News said
Recommends sendbitcoins · 2020-05 · on “Ask HN: What interesting stuff are you browsing?”
"Two Minute Papers" [this video] GTC 2020 Part 2 was pretty good [LINK] Mostly I'm in a rut as well
Recommends SatvikBeri · 2021-02 · on “Medical chatbot using OpenAI’s GPT-3 told a fake patient to kill themselves”
Two minute papers has many fun examples of AIs with unexpected behavior, OpenAI's hide and seek is one of my favorites: [this video]
Cites montenegrohugo · 2021-03 · on “Self-supervised learning: The dark matter of intelligence”
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: [this video] I think we really need to consider how we can mitigate the risk of raising completely ununderstandable yet scarily capable machines.