“Two Minute Papers"”
Channel mention for browsing interesting AI papers.
Full comment
"Two Minute Papers" this video GTC 2020 Part 2 was pretty good link Mostly I'm in a rut as well
OpenAI Plays Hide and Seek…and Breaks The Game! 🤖
11M views · Oct 22, 2019 · 6:02 · 2 HN recommenders · 3 mentions · discussed 2020–2021
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 points people here: HN mentions it as a fun and slightly worrying example of AI systems behaving in unintended ways when optimizing.
“OpenAI's hide and seek is one of my favorites”HN comment, 2021
What Hacker News said 3
“OpenAI's hide and seek is one of my favorites”
Fun example of AI with unexpected behavior.
Full comment
Two minute papers has many fun examples of AIs with unexpected behavior, OpenAI's hide and seek is one of my favorites: this video
“This somewhat humorous but also worrying paper comes to mind”
Example of models doing unintended things when optimizing.
Full comment
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.