Currently pursuing a PhD at the “Mathematics for Our Future Climate” CDT at Reading University.
Previously MSc in applied mathematics/theoretical ML.
Not really active here—racism, Rationality and weirdness in the movement are so bad they made me give up on it.
We don’t know how to align a possible AGI yet. The best we can hope for is that current models are close enough to whatever AGI is going to be, that trying to align them will teach us about aligning an AGI. This task, of trying to align them, is something that shouldn’t just be left to researchers in AI companies.
How can you “solve every possible jailbreak”? And is it worth it crippling large-scale research into safeguarding from future AI because of fears about what the current models might be capable of?
(My own answer is “maybe”. It depends on how bad you think current models are for society—pretty bad in my opinion—vs. how likely you think it is an existentially-threatening AI will actually be born out of the current efforts).
I still maintain that publicly releasing models is the correct way to get any chance of good alignment research—you can’t possibly believe that the researchers at Anthropic alone are enough to tackle the problem. It’s a global problem and should have the opportunity for the global population to solve it.
Being featured on Snopes is sort of a major achievement IMO :)
Where was it published in traditional media?
Thanks for the serious reply!
I guess a “but can’t we, like, just outlaw all war?” approach is not the standard one so I’m at least interested in what answers you may find. Especially with me coming from a very, umm, war-prone country...
No offense Linch, but aren’t these questions for jurists, historians and philosophers? Why should you develop the answers from first principles, so to speak? I’d get writing a blog post about a journey through such sources and what their theories are, but I think trying to answer such questions ourselves is not very robust.
This is not a criticism of you personally—developing ideas that require domain expertise from first principles is an approach I often see in EA and I think it’s a wrong one.
Seems like a good compromise. The examples at the end are also helpful.
About this, however:
The laissez-faire option is flawed because LLM-generated writing is increasingly difficult to detect. There are posts (I’ve seen a lot of these) which have the form of a good quality post which is worth reading, but on closer analysis turn out not to contain any ideas, or just to contain a couple of bullet points’ worth of ideas, surrounded by a lot of fluff and repetition. This leads to quite a large waste of time for the reader.
While this is true, and indeed happens a lot everywhere nowadays, let’s not forget about the option for actual malice—manipulation by posts that look good or convincing but are actually written to persuade you to serve someone’s interests. Which can be done by anyone ranging from individuals, to companies, to industry lobbies to state governments.
Allowing LLM-generated content not only leaves the door open to heaps of slop, but also allows all of this. So some sort of defence is definitely warranted.
The prospects of winning or losing money usually leads to people investigating their views more.
That seems to be a general cultural view in EA, but what I’m saying is that I’ve yet to see any evidence these bets actually help. I think the notion is unfounded.
That’s still a sort of game/cultural thing rather than a means for more positive impact, though. I’ve seen that around EA basically forever, but I don’t think people who bet on their beliefs have been “more right” than those who don’t.
Off topic, but one additional thing I noticed about this list:
I can point to you hundreds of millions of chickens that lay eggs that are out of cages, and I can point to you observable families that are no longer living in poverty. I can show you pieces of legislation that have passed or almost passed on AI. I can show you AMF successes with about 200k lives saved and far lower levels of malaria, not to mention higher incomes and longer life expectancies, and people living longer lives that otherwise wouldn’t be because of our actions.
Is the glaring lack of tangible advances in technical AI safety. It’s a different case from your post, as it’s about a problem rather than a tool; but I think it still shows something about whether we understand the dangers of AI and the systems they stem from enough to do anything about it.
Presumably whoever approved the original donation to buy Wytham Abbey did understand these considerations and decided to go through with it anyway?
To be entirely fair, the comment I linked to for the original cost also explains it was an outside donor—Good Ventures if I’m not mistaken, but I couldn’t find a source for that—who gave the money specifically for this purchase. So EVF is still at a plus, but it’s an… interesting decision on behalf of the donor.
Haven’t seen this anywhere on the forum: Effective Ventures sold Wytham Abbey in February for £5.95 million (source). When they bought it, there were many debates over the price they paid (just under £15 million). Some people said it’s an investment and so it’s not like £15 million have been lost. Well, seems like we now have the verdict on those claims—the whole thing cost about £9 million.
Really cool! I hope it becomes available in the UK soon.
Meanwhile in Israel, Solve is a company offering a whole egg substitute for baking, for 130 ILS for ~50 small eggs (currently ~42 USD, although the war makes the conversion somewhat unrepresentative). I’ve not used it but I’ve heard good things from a gourmet chef. They also sell a “meringue powder”, called Mery Mix by an Italian company, Lapet, at 65 ILS per 1kg(!). Not sure how this converts to eggs.
Yeah I’m not sure what’s with the downvotes.
This is outright the best April Fool’s post we’ve had this year. Shame it didn’t get more views. Seriously, I laughed out loud multiple times.
(I’m Jewish, my grandma was a Holocaust survivor and her father and most of her extended family were killed by the Nazis. My grandfather managed to flee before the war started but some of his family were also killed.)
Thank god we have the April Fool’s tag to protect us from Poe’s law though.
How much of a post are you comfortable for AI to write?
The only parts I’d let AI write are those where I’m unsure if my phrasing is really natural in English and I ask for a better one.
If I’m not the one writing the post, I don’t see why anyone should bother reading it.
But you’re not claiming that the models should only be shared with AI researchers. You’re claiming they should only be shared with AI researchers specifically employed by Anthropic.
Although no, I disagree that the input from non-AI-researchers is useless here—as you need to hear both from the end users and from people affected by AI and its decisions.