LessWrong 2.0 Reader

I'm not sure it classifies as an emotion (nor does stupidity, for that matter), but it probably does exist as a motivation for some human acts, with the relevant emotion usually being anger.  

I don't think your distinction (harm for its own sake, distinct from harm with a motivation) is real, unless you think there are un-caused actions in other realms, or you discount some motivations (like anger or hatred) as "not valid" for some reason.

 

One example of a web of interrelated facts that I have concerns molecular simulations, with bold/italic denoting things that I have in my anki deck, or would make good cards.

One interesting thing about moleculaes bouncing around is that a nanosecond, which sounds really short, is actually a decently long time. Consider that molecules at room temperature are typically moving at about the speed of sound (340 m/s) and a typical chemical bond length is about 0.1 to 0.2 nanometers. This means that a typical molecule (if nothing bumps into it) will go 1700-3400 bond-lengths in a nanosecond! Of course, molecules in liquid, which are jammed pretty close together, won't move that far without interruptions- they'll bump into each other, switch direction and bump into others many times over the course of a nanosecond. This means that the typical timestep (the $dt$ when integrating the differential equations of motion) for a molecular dynamics simulation has to be much shorter. In practice, for a molecular dynamics simulation that simulates all the atoms of a system, $dt$ is about a femtosecond. With these timesteps, it becomes possible to simulate about a microsecond of simulation time per day of all atoms of a medium-sized protein moving around on a modern GPU like an A40. This is a big reason for why we can't just simulate a protein folding to crack the protein folding problem. Protein folding takes about a second or on the order of a million GPU-days if you were to simulate it.

Hrm. My definition of "anti-agathic" is something that prolongs life, so it isn't obviously not counting a brain transplant to a younger body.

I'm somewhat opposed to tweaking the wording on long-standing parts of the census, since that makes it harder to compare to earlier years. If we want to go this route, I'd rather write a new question and ask both some year so we can compare them.

Do you know what topics within AI Safety you're interested in? Or are you unsure and so looking for something that lets you keep your options open?

Hi habryka, I don't really know how best to respond to such a comment. First, I would like to say thank you for your well-wishes, assuming you did not mean them sarcastically. Maybe I have lost the plot, and if so, I do appreciate help in recovering it. Secondly, I feel confused as to why you would say such things in general.

Just last month, me and my coauthors released a 100+ page explanation/treatise on AI extinction risk that gives a detailed account of where AGI risk comes from and how it works, which was received warmly by LW and the general public alike, and which continues to be updated and actively publicised.

In parallel, our sister org ControlAI, a non-profit policy advocacy org focused solely on extinction risk prevention I work with frequently, has had A Narrow Path, a similarly extensive writeup on principles of regulation to address xrisk from ASI, which me and ControlAI have pushed and discussed extensively with policy makers of multiple countries, and there are other regulation-promoting projects ongoing.

I have been on CNN, BBC, Fox News and other major news sources warning in no ambiguous terms about the risks. There is literally dozens of hours of podcast material, including from just last month, where I explain in excruciating depth the existential risk posed by AGI systems and where it comes from, and how it differs from other forms of AI risk. If you think all my previous material has "lost the plot", then well, I guess in your eyes I never had it, not much I can do. 

This post is a technical agenda that is not framed in the usual LW ideological ontology, and has not been optimized to appeal to that audience, but rather to identify an angle that is tractable and generalizes the problem without losing its core, and leads to solutions that address the hard core, which is Complexity. In the limit, if we had beautifully simple, legible designs for ASIs that we fully understand and can predict, technical xrisk (but not governance) would be effectively solved. If you disagree with this, I would have greatly enjoyed your engagement with what object level points you think are wrong, and it may have helped me write a better roadmap.

But it seems to me that you have not even tried to engage with the content of this post at all, and have instead merely asserted it is a "random rant against AI-generated art" and "name-calling." I see no effort other than surface level pattern matching, or any curiosity to how it might fit with my previous writings and thinking that have been shared and discussed.

Do you truly think that's the best effort at engaging in good faith you can make? 

If so, I don't know what I can say that would help. I hope we can both find the plot again, since neither of us seem to see it in the other person.

One thing that's useful for me is to draw analogies. For instance, the earth is about as big compared to the kilogram as benzene ($1.3\times {10}^{-25}$ kg) is small.

That's true. The specific energy of antimatter is also actually double the "maximum" if you don't count the mass of the matter (1 gram of antimatter + 1 gram of air produces about 2 grams worth of energy). Funny enough, this is analogous to combustion fuel. The reason combustion fuel (on the order of 50 MJ/kg for most hydrocarbons) seems to be able to store much more energy than, say a high explosive (on the order of 5 MJ/kg) is because high explosives contain their own oxidizers, while combustion fuel uses the air as an oxidizer.

Ah, yeah, sorry. I do think about this distinction more than I think about the actual model-based vs model-free distinction as defined in ML. Are there alternative terms you'd use if you wanted to point out this distinction? Maybe policy-gradient vs ... not policy-gradient?

I've uploaded the code to github.

Nice to hear people are making room for uncomfortable honesty and weirdness. Wish I could have attended.