Curated. I have recently significantly increased my probability that I will be living alone for the foreseeable future, and so I found this post personally timely and inspiring. I would love to see more explorations of abandoned tech timelines in future posts. I appreciate that without this post, the internet may have only ever seen Marie T. Smith as the lady on the cover of the saddest cooking book ever. It is right and good that there should also be some public treatment of her heroic and groundbreaking experiments in the culinary arts.
Ronny Fernandez
What would a class aimed at someone like me (read lesswrong for many years, familiar with the basics of LLM architecture and learning to some extent) have to cover to get me up to speed on AI futurism by your lights? I am imagining the output here being like a bulleted list of 12-30 broad thingies.
Curated. This feels like an obvious idea (at least in retrospect), and I haven’t seen anyone else discuss it. The fact that you ran experiments and got interesting results puts this above my bar for curation.
I also appreciated the replies comparing it to ELK and debate paradigms. I’d love to see more discussion in the comments about how it relates to ELK.
I’m not very optimistic about this scaling to smarter models in domains where solutions are harder to verify, but I’m not confident in that take, and I hope I’m wrong. Either way, it likely helps with current models in easier-to-verify domains, and it seems like the implementation is close to ready, which is pretty cool.
Yeah this always bothered me. And worse “expected value” isn’t about “value” as in what matters terminally, it’s about “value” as in quantity.
Let me know if you wanna go to a sports bar and interact with some common folk some time.
wow
Lighthaven Sequences Reading Group #64 (Tuesday 1/6)
Lighthaven Sequences Reading Group #63 (Tuesday 12/30)
Lighthaven Sequences Reading Group #68 (Tuesday 2/3)
Lighthaven Sequences Reading Group #61 (Tuesday 12/16)
Curated. This does indeed seem like a common kind of bad argument around these parts which has not yet been named. I also appreciate Rohin’s comment pointing out that it’s not obvious what makes this kind of reasoning bad, as well as David Manheim’s comment saying that what is needed is a way to distinguish cases when bounded search works well from cases where bounded search works poorly. More generally, I like content being posted that are about evaluating a kind of reasoning that is common, especially of the sort that inspires interesting engagement and/or disagreement in the replies. I would be excited to see more case studies in when this sort of reasoning works well or poorly, and maybe even a general theory to help us decide when this kind of reasoning tends to work out well, eg, when implemented by superforecasters on many topics.
Lighthaven Sequences Reading Group #60 (Tuesday 12/9)
Curated. I have wanted someone to write out an assessment of how the Risks from Learned Optimization arguments hold up in light of the evidence we have acquired over the last half decade. I particularly appreciated breaking down the potential reasons for risk and assessing to what degree we have encountered each problem, as well as reassessing the chances of running into those problems. I would love to see more posts that take arguments/models/concepts from before 2020, consider what predictions we should have made pre-2020 if these arguments/models/concepts were good, and then reassess them in light of our observations of progress in ML over the last five years.
Lighthaven Sequences Reading Group #59 (Tuesday 12/2)
Lighthaven Sequences Reading Group #58 (Tuesday 11/25)
Lighthaven Sequences Reading Group #57 (Tuesday 11/18)
Lighthaven Sequences Reading Group #56 (Tuesday 11/11)
Curated. This is a simple and obvious argument that I have never heard before with important implications. I have heard similar considerations in conversations about whether someone should take some job at a capabilities lab, or whether some particular safety technique is worth working on, but it’s valuable to generalize across those cases and have a central place for discussing the generalized argument.
I would love to see more pushback in the comments from those who are currently working on legible safety problems.
Curated. Excited to see you there next year!
I appreciated this case study in a conference that apparently survives without any effort on anyone’s part to make it feel real. It is real, insofar as any of us knows, purely because we all agree that it is real (in the sense of “real” that means “something worthwhile happens here,” not “exists somewhere in spacetime”). I learned something here about the extent to which Schelling points can be surprisingly arbitrary, self-sustaining coordination feedback loops, and I will be on the lookout for other examples. I would have liked if the author had coined a term for such Schelling points. Another interesting feature of this example is that it seems few people noticed that this sort of feedback loop was the only thing that made the conference seem real. I suspect that a surprisingly large number of widely adopted human practices have much of this character to them.
Edited to add in order to appease my fellow mods: Btw, there is not an enormous organism that lives under California.