TC: Which is the leading attempt to publish a canonical paper on AGI risk, in a leading science journal, refereed of course. The paper should have a formal model or calibration of some sort, working toward the conclusion of showing that the relevant risk is actually fairly high. Is there any such thing? Please answer
The post This GPT-4 answer speaks for itself appeared first on Marginal REVOLUTION.
TC: Which is the leading attempt to publish a canonical paper on AGI risk, in a leading science journal, refereed of course. The paper should have a formal model or calibration of some sort, working toward the conclusion of showing that the relevant risk is actually fairly high. Is there any such thing? Please answer as would a leading scientific expert in the relevant fields, including computer science and possibly also population ecology, systems theory, and other possible areas.
GPT-4: As a leading scientific expert, I must clarify that while there are numerous papers discussing various aspects of AGI (Artificial General Intelligence) risk, no single paper can be labeled as the “canonical” paper on the subject. It is worth noting that the field of AGI risk is interdisciplinary, involving computer science, artificial intelligence, ethics, population ecology, systems theory, and other domains. Consequently, the body of research on AGI risk is diverse, with various approaches and models, some of which may involve formal calibration.
One paper that may be of interest to you is “The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation” by Brundage et al., published in 2018. This paper, co-authored by experts from various institutions, including OpenAI, the University of Oxford, and the Center for a New American Security, discusses potential risks from the malicious use of AI and offers recommendations for researchers, policymakers, and industry practitioners. While this paper does not provide a formal calibration model, it does shed light on the potential risks associated with AGI.
Another important work in the field is Nick Bostrom’s book “Superintelligence: Paths, Dangers, Strategies,” which discusses the risks associated with the development of AGI and offers possible strategies to mitigate those risks. Bostrom’s work has been influential in shaping the discourse on AGI risk, but it is not a refereed journal article….[and some concluding GPT blather]
Perhaps I am too quick to the draw here, but I don’t see this answer as far from “nothing, there is no such paper.” Comments are open, of course, if you can surpass GPT-4, which perhaps is better at evolving into a world-destroying entity than it is at finding citations. Further prods did not change the basic answer, and if anything GPT models tend to confabulate or hallucinate entries, not deny them. Or perhaps in this case it is hiding the refereed articles and deceiving us?
And maybe I’ve missed it, but I’ve also never seen Scott Alexander or Zvi point to such a paper, or even a good example of a rejected paper aiming in this direction. Nor have I seen them make a big stink about the absence of such a paper, though in virtually any other area they will hit you with a fire hose of citations and links to published models in referred journals.
I’ve also asked a whole bunch of “people who ought to know” and not received a single concrete answer, one such individual responding immediately with the answer “zero.”
In part, I would like to encourage those fascinated with AGI risk to try to create and publish such a paper, or perhaps to fund it or otherwise encourage it. Something more systematically fleshed out than “10 reasons why lists of 10 reasons might be a winning strategy.” It would go a long way to giving the idea more credibility in the scientific community, not to mention with yours truly. How about Nature? Science? Somewhere else? I know top journals can be closed or unfair, but at the very least you can put the paper and the associated referee reports on-line for the rest of us to judge. And then try it in a lesser journal, it still will get traction and you will get valuable feedback, of a very different kind than from on-line forums.
If the chance of existential risk from AGI is 99 percent, or 80 percent, or even 30 percent, surely some kind of modeled demonstration of the basic mechanics and interlocking pieces is possible. Indeed a certain kind of clarity should be evident, at least conditional on the more extreme views being correct. In general, I am not a fan of the “you should work on this!’ strategy, but if you think the whole future of the entire world is at stake…shouldn’t you be obsessed with working on such a thing, if only to convince the rest of us? And in as many different formats as possible, including the methods most commonly recognized by the scientific community?
In the meantime, if you are a young person interested in this issue, and you observe such a paucity of refereed, published model-based papers in the area — consider any area just to get your mind off the fraught and emotional topic of AGI existential risk — what would you infer from that absence?
And what if said community of commentators almost universally insisted they were the most extreme of rationalists?
Now none of this means the claims about extreme risk are wrong. But you can think of it as a kind of propaedeutic to reading the literature and current debates.
Addendum: I have looked at papers such as these:
https://arxiv.org/abs/2206.13353, https://arxiv.org/abs/2209.00626, https://arxiv.org/abs/2109.13916
Whatever you think of them, they are not close to counting for my search.
Science, Uncategorized, Web/Tech