Multi-Agent Hide and Seek

What Hacker News said

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

Specialized AI is unlikely to be a threat. The issue will be with general AI, and simple but not fully thought out utility functions. This short video makes the concern much more real: [this video] Consider what would happen if you took that same AI, make its utility function similar to this: [LINK] , and released it on the internet.

Cites willhk · 2019-12 · on “Dota 2 with Large Scale Deep Reinforcement Learning [pdf]”

The work I've seen recently from them on multi-agent play seems to indicate this is a problem they're very successfully working on. [this video]

Cites ShamelessC · 2021-12 · on “What Does It Mean for AI to Understand?”

In statistics and machine learning this problem is called concept drift and it's an open research problem. Indeed all the models I listed are already out-of-date with the present state of the world; unless they are fine-tuned on new data. The regime for the above networks is called "pre-training". The idea here is that rather than training _directly_ on some challenging, specific task, you instead train a more generic task on a _lot_ of data. This gives you a "backbone model" that winds up being very strong on more specific tasks as well. In many cases, the ability to (cheaply) curate or create enough accurate data for specific sub-tasks might not even be possible. It's easier to scrape 400

Cites HaukeHi · 2022-03 · on “It looks like you’re trying to take over the world”

I think evolution is not an undirected process in that sense because it's an optimization process, that optimizes to create more copies of itself. Superintelligence will likely use some Evolutionary Computation (see en.wikipedia.org/wiki/Evolutionary_computation ). Also see Karl Sims 'Creatures' from the 90s: youtube.com/watch?v=JBgG_VSP7f8 or OpenAI's Multi-Agent Hide and Seek: [this video]

Cites treesprite82 · 2022-07 · on “Forget the hype, “thinking machines” can’t replace humans”

> There's just something I can't describe with words about what it lacks today - where it's possibly more philosophical than technical My personal viewpoint is that there's nothing inherently special about biological intelligence that can't theoretically be reproduced with electronics, but that today's AI has some practical limitations like no significant persistent internal state. I saw an "Inner Monologue" paper by Google Robotics recently which could be a step in the right direction. > Humans for example operate within the universal set and within all dimensions we can percieve. Our brain's direct output is electrical signals to a set of muscles. I don't think there's anything in particul

Cites PartiallyTyped · 2022-09 · on “On Device Learning”

Here [1]. They called it "emergent" property, but I only see that as inevitable behaviour. [1] [this video]

Cites HanClinto · 2024-07 · on “Prover-Verifier Games improve legibility of language model outputs”

True RL is not limited by being tethered to human-annotated data, and it is able to create novel approaches to solve problems. True RL requires a very clear objective function (such as the rules of Go, or Starcraft, or Taboo!) that the model can evaluate itself against. Andrej Karpathy talks about the difference between RLHF and "true" RL here: [LINK] > The other thing is that we're doing reinforcement learning from human feedback (RLHF), but that's like a super weak form of reinforcement learning. I think... what is the equivalent in AlphaGo for RLHF? What is the reward model? What I call it is a "vibe check". Imagine if you wanted to train an AlphaGo RLHF, it would be giving two people two