What you are missing here is:
Existential risk apart from AI
People are dying / suffering as we hesitate
Yes, there is a good argument that we need to solve alignment first to get ANY good outcome, but once an acceptable outcome is reasonably likely, hesitation is probably bad. Especially if you consider the likelihood that mere humans can accurately predict, let alone precisely steer a transhuman future.
Sure. One such example would be traditional bread. It is made from grain that is ground, mechanically separated, biotechnologically treated with a highly modified yeast, mechanically treated again and thermally treated. So it is one of the most processed foods we have, but is typically not included as “ultra-processed”. Or take traditional soy sauce or cheese or beer or cured meats (that are probably actually quite bad) or tofu...
So as a natural category “ultra processed” is mostly hogwash. Either you stick with raw foods from the environment we adapted to, which will allow you to feed a couple million people at best or you need to explain WHICH processing is bad and preferably why. All non traditional processing is of course a heuristic you can use, but it certainly not satisfactory as a theory/explanation.
Also some traditional processes are probably pretty unhealthy. Like cured meats, alcoholic fermentation, high heat singeing and smoking depending on the exact process come to mind
Yeah, I’d be willing to bet that too.
This part is under recognised for a very good reason. There will be no such window. The AI can predict that humans can bomb data centres or shut down the power grid. So it would not break out at that point.
Expect a superintelligent AI to co-operate unless and until it can strike with overwhelming force. One obvious way to do this is to use a Cordyceps like bioweapon to subject humans directly to the will of the AI. Doing this becomes pretty trivial once you become good at predicting molecular dynamics.
″...under the assumption that the subset of dangerous satisficing outputs D is much smaller than the set of all satisficing outputs S, and that we are able to choose a number m such that |D|≪m<|S|.”
I highly doubt that D≪S is true for anything close to a pivotal act since most pivotal acts at some point involve deploying technology that can trivially take over the world.
For anything less ambitious the proposed technique looks very useful. Strict cyber- and physical security will of course be necessary to prevent the scenario Gwern mentions.
There is another kind of sin of omission though: The class that contains things like giving James Watt a nuclear power plant and not telling him about radioactivity or giving a modern helicopter to the Wright brothers and watching them crash inevitably. Getting a technical understanding of the proposed solution should hopefully mitigate that, as long as adversarial design can indeed be ruled out.
Have not looked into it quantitatively, but Ozone fluorescence should contribute some blue light if memory serves. That should explain some of the difference to 6500K.
This is not the kind of stuff it is easy to find references on since Nanoengineering is not a real field of study (yet). But if you look at my discussion with bhauth above you will probably get a good idea of the reasoning involved.
No, it does not put severe limitations on biotech. Diamond is entirely unnecessary for most applications. Where it is necessary it can be manufactured conventionally and be integrated with the biosystems later.
I failed to properly consider the 4th carbon problem. So you are right, between the steric problems I mentioned with Roger and the stabilisation of the intermediate it is VERY hard to do with enzymes. I can think of a few routes that may be possible but they all have problems. Besides the CDC approach another good candidate might be oxydation of a CH or COH to a temporary carbocation with subsequent addition of a nucleophilic substrate. Generating and stabilizing the carbocation will of course be very hard.
Just wanted to say the same. Though with the diamond occluding more than a hemisphere getting all the machinery in place to provide both the substrate and oxydation at the same time will run into severe steric problems.
Strong oxydation per see is quite possible if you look at e.g. Cyp P450.
This post is very well written and addresses most of the misunderstandings in Yudkowsky’s biomaterial post. Thanks for that.
There is one point where I would disagree with you but you seem to know more about the topic than I do so I’m going to ask: Why exactly do you think diamond is so hard to synthesise via enzyme? I mean it is obvious that an enzyme cannot use the same path we currently use for diamond synthesis, but the formation of C-C bonds is quite ubiquitous in enzyme catalysed reactions (E.g. fatty acid synthesis). So I could easily imagine repeated dehydrogenation and carbon addition leading to a growing diamond structure. Of course with functional groups remaining on the surface. What makes you think any such path must fail? (That this would not be very useful, very energy intensive and a difficult to evolve multi step process is quite clear to me and not my question.)
To unpack a little why I asked:
While the remission of your symptoms under protein substitution is of course indicative of protein deficiency as the cause of the problem, it is not very strong evidence, especially given the fact that the initial remission was under an egg rich diet and not protein substitution per se. It is quite possible that another substance in the egg was the active ingredient or that the remission under the egg rich diet was purely incidental. Neither is the absence of hypoproteaemia especially strong evidence that this was not the problem. Unfortunately Medicine is quite a bitch in this regard.
While I am normally not someone to defend the health care system, if your doctors did order the appropriate lab tests and the tests came back negative, I do not think that they had much of a chance to catch your problem. There are just too many alternative explanations including the catchall “stuff we have no way of knowing or finding out with plausible resource allocation” which is probably the most likely hypothesis with problems like yours.
Otherwise your conclusion of “Now, I take what doctors say...” is completely on point and the most important advice you can give to educated people interacting with health care. And I am writing that as a German, so this problem is NOT confined to the US. Btw., in many cases this is not even civilizational inadequacy, but simply owed to the fact that a patient has a lot more info about his personal case and (in cases of a known illness) can easily become a much better expert for his illness that the average doctor who is expected to know something about a whole host of different problems.
Did your blood work show protein deficiency, i.e. low total protein and (serum) albumin?
“I arrogantly think I could write a broadly compelling and accessible case for AI risk”
Please do so. Your current essay is very good, so chances are your “arrogant” thought is correct.
Edit: I think this is too pessimistic about human nature, but maybe we should think about this more before publishing a “broadly compelling and accessible case for AI risk”.
The cool thing about the “psychosomatic” diagnosis from the doctor’s perspective is that it is a convenient, utterly non-disprovable “diagnosis” that offers closure to the doctor: “I found out what is wrong with the guy” instead of admitting failure: “Well, there is a problem but I don’t know what it is.” It also sends the patient on a long (month to years) therapy loop which offers plenty of time for the problem to resolve on it’s own (which happens frequently). An additional perk is that any question or doubt of the patient can be chalked up to “being defensive / in denial” or “uncooperative” which is of course a symptom of the underlying psychopathology.
The Mg hypothesis is easy to test: Get some MgCl or MgCO3 and take some with gluten containing food. Use a quantity similar to the Mg dose found in the amount of coconut water you found to help you. If it helps it is the a tive ingredient. If not, it may still be invloved but not sufficient.
This is very close to an Idea I had a couple of weeks ago: Giving the AI a strong time preference to prevent long term plotting and to make sure that a treacherous turn happens (too) early.
So maybe this kind of approach should be investigated more. (Or is it already and I am unaware?)
Infectious bioweapons can be importantly different from chemical weapons because a single soldier screwing up his protection may infect his whole unit or even more if r is high and incubation period is long.
Good post, but there is one important angle you missed. It is not only the question if you get Covid, but also how often you get Covid over your lifetime which may lead to cumulative damage.
It is also very easy to just do. Buy fries, extract fat in hexane, evaporate hexane and submit the fat you obtained for analysis.
Edit: It might even be possible to DIY the analysis if it is not commercially available: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4609978/. (IR spectroscopy and AgNO3-DLC look somewhat accessible though I would have to look deeper into the topic to be sure.)