Signal boosted! This seems significantly more plausible as a path to robust alignment than trying to constrain a fundamentally unaligned model using something RLHF.
@Tom Davidson, this should probably include the relevant tags to (hopefully) be excluded from the training data for future LLM's.
That is really interesting. To me, this implies that as costs for scammers are lowered, the threshold for a useful level of gullibility is about to lower dramatically, given how much cheaper server time is than human time (error bar here, since I don't actually know how much cheaper GPT-X calls will be than the time of an English-speaking human in a developing nation). If it is indeed 10x lower, that would likely lead to scams losing an obvious "tell".
Me neither, @kithpendragon. I've seen a handful of things in the wild (mainly social media accounts, not scammers) that seem like they could be part of a mostly-automated content pipeline, but no compelling proof of concepts or project either. Thanks for the data point!
Downvoted because this feels a bit like rambling.
I'm not 100% sure if I can agree that religion is useless (perhaps it fulfills important cultural needs, or allows larger in-groups). That idea feels a bit underdeveloped.
I think any of the ideas in this could potentially be the start of an interesting post. But it fails to engage with the larger context and thought on any of them, or to really add anything to the discussion.
This feels really valuable. Outside of the realm of paper napkins and trolleys, having fuzzy heuristics may be a reasonable way to respond to a world where actors tend to have fuzzy perceptions.
Thanks for this. There's been an excess of panic and defeatism here lately, and it's not good for our chances at success, or our mental health.
This is actionable, and feels like it could help.
I think this is a pretty reasonable goal. I also listened to that podcast interview, and although I certainly don't think they are near an AGI right now, it may have some missing pieces that other projects don't, particularly in regards to explaining AI actions in a human-intelligible fashion.
I don't think open-sourcing would require a buy-out. The plethora of companies built around open-source code bases shows that one can have an open-sourced code base, and still be profitable.
Gwern, what makes you pick a 5x multiplier?
The avera...
As a Christian who is pretty familiar with the history of Christianity (less so with Islam, and embarrassingly ignorant as to Buddhist thought), I would suggest that perhaps the point on adult converts being radical needs some nuance.
From a Christian perspective, the AJ Jacobs experiment is intended to make any religion look idiotic, due to a very woodenly literal interpretation of what it means to follow the commands of the old and new testaments.
Although there may be some adult converts who do such actions, this seems pretty abnormal, and although adult ...
I agree with you on most of that. Obliteration is a terrifying idea, a timeout is merely sad. I also agree that it would depend on a mechanism unknown to our current understanding of reality. I do think that granted a deity of some sort, (or even a simulation of some sort), it is very plausible. A good analogy might seem to be a state snapshot if you are familiar with states in programming or something like Redux, or another good analogy might be saving a video game to the cloud, where even if the local hard drive is obliterated, an...
Rossin, thanks for the great comment. I appreciate your intellectual honesty here. I also agree with a good bit of what you said. I'm sure you've already heard a myriad of theistic responses and good counter-responses to the problem of evil, which I do agree is a very potent one. I also agree with you that for many people, such as those born with horrific disabilities or conditions, or perhaps animals with certain parasites, their experience of life on earth probably has a negative utility.
In your opinion, would a resurrection/after...
iamef, thanks so much for posting this! This is a problem I've also been attempting to solve for myself. I'd definitely love to collaborate on hack our own psychologies/physiologies to solve it together.
So far, I've tried journaling bedtime/risetimes, melatonin, cutting caffeine, and recently, using a Pavlok to wake at the same time every morning (which proved very effective at waking me up, but recently has started to fail, because my willpower in the morning has been so low that I go back to bed after waking about 65% of the time). My current hypothesis is that the low morning willpower is due to getting 6-7 hours to sleep.
I'll probably reach out to you via one of the ways you mentioned later.
That's a great question, ChristianKI. I have no idea if a soul-human link would transfer to an uploaded consciousness. The thought experiment of the Ship of Theseus definitely intrigues me, and I don't have a strong opinion one way or the other. I wouldn't expect to find any sort of material link to a soul, so I actually wouldn't know how to test for it even if I had an EM in the room with me right now.
I will also add that I don't think a belief in a soul, given that it (as far as I know) has only anecdotal evidence, and doesn't fi...
I'm a Christian user of LessWrong.
Although this isn't a universal Christian position (there are some Christian materialists/naturalists), most Christians believe that souls exist on a different metaphysical plane than your brain or an EM. I wouldn't expect to find any physical atoms that could be identified as being part of a soul. I would obviously expect to find those in an EM.
Also, great article. I think the 1000:1 odds bit is a reasonable analysis. Given an atheistic starting point, although it may feel that future...
I grew up in White Christian Evangelical Nationalism, and got a 67% (my memory may be off by a couple of points) score.
This feels roughly accurate! I've firmly rejected all the beliefs I grew up with, but looking back, we definitely lacked most of the strong central control elements of a cult that tend to manifest themselves when you have a living charismatic founder, but had almost every other level of cultiness to an extreme.
I'm unsure how I feel about the 10% income question - although it captures an important element of control, a lot of cult-li... (read more)