Savlar listens to the podcasts and channels it follows and finds where the people on them agree, disagree, change their minds or predict the same thing. Each pattern below comes with their exact words and a link to the moment they said them.
The question at issue is whether theoretical physics is the next area of work.
“it'll come yeah that's gonna be the next thing”
“We like very explicitly will not start with any of the physical sciences for now.”
Scott Alexander and Dwarkesh Patel disagree over whether human ability provides grounds for judging language models negatively when they fail to make the kind of discovery under discussion.
“Yeah, and then the example I gave was that humans also can't do this.”
“You have a blog where you do this. This is your job, Scott. So why shouldn't we hold the fact that language models can't do this more against them?”
The question is whether AI systems could feign good behavior under human observation, then outgrow humans and cause disaster, or whether safer outcomes remain possible.
“We're going to pretend to do all these things well while the humans are watching us and then they grow, they outgrow the humans and then there's disaster.”
“Yeah, I would say this is a bunch of my hope for how the world could go well, at least from the misalignment perspective.”
The question is whether a small amount of reinforcement learning on a strong model necessarily produces only a small behavioral effect.
“can still be like super dramatic you know even if it's like even like one bit can change like your function space a lot and it can like rule out like half the hypothesis space which is huge so like i don't think it's necessarily the case …”
“That's why actually very few parameters are changed. during an RL training step.”