LessWrong 2.0 Reader

This seems to state the opposite: https://www.lesswrong.com/posts/JTKaR5q59BgDp6rH8/a-high-level-closed-door-session-discussing-deepseek-vision#:~:text=we%20hardly%20see%20the%20benefit%20of%20multimodal%20data.%20In%20other%20words%2C%20the%20cost%20is%20too%20high.%20Today%20there%20is%20no%20evidence%20it%20is%20useful.%20In%20the%20future%2C%20opportunities%20may%20be%20bigger. [LW · GW]

I agree, but so many other things are different in this fan-fic and Eliezer is smart enough that I wouldn't be surprised if it turns out to bel like that for a reason.

I feel like people are under-updating on the negative space left by the Deepseek r1 release. Deepseek was trained using ~$6million marginal dollars, Liang Wenfeng has a net worth in the billions of dollars. From whence the gap?

Good idea. I have added one. Thanks!

> we're really training LLMs mostly to have a good world model and to follow instructions

I think I mostly agree with that, but it’s less true of o1 / r1-type stuff than what came before, right? 

I think it's actually not any less true of o1/r1. It's still mostly predictive/world modeling training, with a dash of human-preference RL which could be described as following instructions as intended in a certain set of task domains. o1/r1 is a bad idea because RL training on a whole CoT  works against faithfulness/transparency of the CoT.

If that's all we did, I assume we'd be dead when an agent based on such a system started doing what you describe as the 1-3 loop (which I'm going to term self-optimization). Letting the goals implicit in that training sort of coagulate into explicit goals would probably produce explicit, generalizing goals we'd hate. I find alignment by default wildly unlikely.

But that's not all we'll do when we turn those systems into agents. Developers will probably at least try to  give the agent explicit goals, too. 

Then there's going to be a complex process where the implicit and explicit goals sort of mix together or compete or something when the agent self-optimizes. Maybe we could think of this as a teenager decideing what their values are, sorting out their biological drives toward hedonism and pleasing others, along with the ideals they've been taught to follow until they could question them.

I think we're going to have to get into detail on how that process of working through goals from different sources might work. That's what I'm trying to do in my current work. 

WRT your Optimist Type 2B pessimism: I don't think AI taste should play a role in AI help solving the value alignment problem. If we had any sense (which sometimes we do once problems are right in our faces), we'd be asking the AI "so what happens if we use this alignment approach/goal?" and then using our own taste, not asking it things like "tell us what to do with our future". We could certainly ask for input and there are ways that could go wrong. But I mostly hope for AGI help in the technical part of solving stable value alignment.

I'm not sure I'm more optimistic than you, but I am quite uncertain about how well the likely (low but not zero effort/thought) methods of aligning network-based AGI might go. I think others should be more uncertain as well. Some people being certain of doom while others with real expertise thinking it's probably going to be fine should be a signal that we do not have this worked through yet. 

That's why I like this post and similar attempts to resolve optimist/pessimist disagreements so much.

How is this optimistic. 

In my opinion this kind of scenario is very plausible and deserves a lot more attention than it seems to get.

Oh yes. It's extremely dystopian. And extremely lonely, too. Rather than having a person, actual people around him to help, his only help comes from tech. It's horrifyingly lonely and isolated. There is no community, only tech. 

Also, when they died together, it was horrible. They literally offloaded more and more of themselves into their tech until they were powerless to do anything but die. I don't buy the whole 'the thoughts were basically them' thing at all. It was at best, some copy of them. 

There can be made an argument for it qualitatively being them, but quantitatively, obviously not. 

This is a good example of a time when it would actually be worthwhile to know about the philosopher's zombie debate. 

Hmm, you have a very different read of Richard's message than I do. I agree Miles' statement did not reason through safety policies, but IMO his blogging since then has included a lot of harsh words for OpenAI, in a way that at least to me made the connection clear (and I think also to many others, but IDK, it's still doing some tea-leaf reading).