DeepMind: Generally capable agents emerge from open-ended play — LessWrong

lesswrong.com · 5,889 words · saved by 1 readers

My hot take: This seems like a somewhat big deal to me. It's what I would have predicted, but that's scary, given my timelines. I haven't read the paper itself yet but I look forward to seeing more numbers and scaling trends and attempting to extrapolate... When I do I'll leave a comment with my thoughts. EDIT: My warm take: The details in the paper back up the claims it makes in the title and abstract. This is the GPT-1 of agent/goal-directed AGI; it is the proof of concept. Two more papers down the line (and a few OOMs more compute), and we'll have the agent/goal-directed AGI equivalent of GPT-3. Scary stuff. This is certainly interesting! To put things in proportion though, here are some limitations that I see, after skimming the paper and watching the video: Thanks! This is exactly the sort of thoughtful commentary I was hoping to get when I made this linkpost. --I don't see what the big deal is about laws of physics. Humans and all their ancestors evolved in a world with the same

x DeepMind: Generally capable agents emerge from open-ended play — LessWrong DeepMind Machine Learning (ML) Reinforcement learning AI Capabilities General intelligence AI Frontpage 248 DeepMind: Generally capable agents emerge from open-ended play by Daniel Kokotajlo 27th Jul 2021 AI Alignment Forum 2 min read 53 248 Ω 75 This is a linkpost for https://deepmind.com/blog/article/generally-capable-agents-emerge-from-open-ended-play EDIT: Also see paper and results compilation video ! Today, we published " Open-Ended Learning Leads to Generally Capable Agents ," a preprint detailing our first ste

DeepMind: Generally capable agents emerge from open-ended play — LessWrong

related reading