During the LessWrong 1.0 Wiki Import we (the LessWrong team) discovered a number of great articles that most of the LessWrong team hadn’t read before. Since we expect many others to also not have have read these, we are creating a series of the best posts from the Wiki to help give those hidden gems some more time to shine.
The original wiki article was fully written by Kaj Sotala, who I’ve added as a coauthor to this post. Thank you for your work on the wiki!
AI advantages are various factors that might favor AIs in case there was ever a conflict between them and humans. These can be classified as hardware advantages, self-improvement capabilities, co-operative advantages, and human handicaps.
Hardware advantages
Superior processing power: Having more serial processing power would let an AI think faster than humans, while having more parallel processing power and more memory would let it think about more things at once.
Self-improvement capabilities
An AI with access to its source code may directly modify the way it thinks, or create a modified version of itself. An AI can intentionally be built in a manner that is easy to understand and modify, and may even read its own design documents. Self-improvement capabilities may enable recursive self-improvement to occur, thereby triggering an intelligence explosion.
Improving algorithms: An AI may modify its existing algorithms, e.g. making them faster, to consume less memory, or to rely on fewer assumptions.
Designing new mental modules: A mental module is a part of a mind that specializes in processing a certain kind of information. An AI could create entirely new kinds of modules, custom-tailored for specific problems.
Modifiable motivation systems: Humans frequently suffer from problems such as procrastination, boredom, mental fatigue, and burnout. A mind which did not become bored or tired with its work would have a clear advantage over humans.
Co-operative advantages
Copyability: A digital mind can be copied very quickly, and doing so has no cost other than access to the hardware required to run it.
Perfect co-operation: Minds might be constructed to lack any self-interest. Such entities minds could share the same goal system and co-operate perfectly with one another.
Superior communication: AIs could communicate with each other at much higher bandwidths than humans, and modify themselves to understand each other better.
Transfer of skills: To the extent that skills can be modularized, digital minds could create self-contained skill modules to be shared with others.
Human handicaps
Humans frequently reason in biased ways. AIs might be built to avoid such biases.
Biases from computational limitations or false assumptions: Some human biases can be seen as assumptions or heuristics that fail to reason correctly in a modern environment, or as satisficing algorithms that do the best possible job given human computational resources.
Human-centric biases: People tend to think of the capabilities of non-human minds, such as God or an artificial intelligence, as if the minds in question were human. This tendency persists even if humans are explicitly instructed to act otherwise.
Biases from socially motivated cognition: It has also been proposed that humans have evolved to acquire beliefs which are socially beneficial, even if those beliefs weren’t true.
References
Kaj Sotala (2012): Advantages of Artificial Intelligences, Uploads, and Digital Minds. International Journal of Machine Consciousness 4 (1), 275-291.
A few more ideas:
How does “Quality intelligence” fit into this? For example, being disposed to come up with more useful concepts, more accurate predictions and models, more effective strategies, more persuasive arguments, more creative ideas. Perhaps the author meant quality intelligence to be subsumed under human handicaps or something, but I feel like it deserves its own section. It seems to me to be probably the most important of all the advantages AI might have.
This is a minor one, but: AIs run on servers rather than bodies. They can be downloaded onto hard drives and transported or hidden very easily. (Including over the internet!) In some scenarios AIs have the disadvantage here (e.g. when it takes a supercomputer to run an AI and there is a war, the supercomputers can be targeted and destroyed) but in most scenarios AIs have the advantage, I think. (Easy to assassinate even well-defended human leaders and scientists, almost impossible to assassinate even a poorly-defended AI, since all they need is a backup copy stored somewhere.)
Another minor one: Humans need to sleep, AIs don’t, at least not current designs. In intense competitions and conflicts that take place over a few days, this is most important; in competitions that take place over months it is more like, idk, a 3% efficiency gain from not having to delegate to the night-shift leader (risking occasionally delegating too much or too little). (In conflicts that last only a few days, important decisions are numerous and urgent enough that there’s no way to delegate them efficiently between leaders, and you have to either let your best leader go sleepless or accept that your second-best leader will be taking some important decisions.) (This is all my armchair speculation btw, not super trustworthy lol)
EDIT to add more:
Humans typically come with certain nonconsequentialist behaviors built-in, e.g. a sense of fairness, a tendency to get angry and take revenge under certain conditions, etc. Thus humans have certain somewhat-credible commitments that benefit them in most circumstances. This may be a disadvantage of AI, except that I suspect AIs might be able to make an even wider range of even more credible commitments. At least in principle they could. This is a broadly useful thing which is more powerful than it might seem; it helps you build and maintain coalitions and agreements while also helping you get more of what you want in bargaining and conflict situations. For more on this, see the commitment races problem.
Novelty. There is a data asymmetry that probably favors AI over humans in conflicts: There is loads of data on humans and how they behave, but there will be comparatively little on AIs. It’s as if an alien landed on earth, and had access to Earth’s internet and history books, but no human had access to alien internet or history books. An advantage like this may have been part of the explanation for why the conquistadors were able to conquer so much so easily.
I think I meant this to be covered by “designing new mental modules”, as in “the AI could custom-design a new mental module specialized for some particular domain, and then be better at coming up with more useful concepts etc. in that domain”. The original paper has a longer discussion about it:
The “hardware advantages” section also has this:
I feel like neither of those things fully captures quality intelligence though. I agree that being able to design awesome modules is great, but an AI could have a quality intelligence advantage “naturally” without having to design for it, and it could be applied to their general intelligence rather than to skill at specific domains. And I don’t think parallelism, working memory, etc. fully captures quality intelligence either. AWS has more of both than me but I am qualitatively smarter than AWS.
To use an analogy, consider chess-playing AI. One can be better than another even if it has less compute, considers fewer possible moves, runs more slowly, etc. Because maybe it has really good intuitions/heuristics that guide its search.
Note that in my framing, there is no such thing as general intelligence, but there are specific domains of intelligence that are very general (e.g. reasoning with if-then statements). So under this framing, something having a general quality intelligence advantage means that it has an advantage in some very generally applicable domain.
Having good intuitions/heuristics for guiding search sounds like a good mental module for search to me.
I think I could define general intelligence even in your framing, as a higher-level property of collections of modules. But anyhow, yes, having good intuitions/heuristics for search is a mental module. But it needn’t be one that the AI designed, heck it needn’t be designed at all, or cleanly separate from other modules either. It may just be that we train an artificial neural net and it’s qualitatively better than us and one way of roughly expressing that advantage is to say it has better intuitions/heuristics for search.
I think the cooperative advantages mentioned here have really been overlooked when it comes to forecasting AI impacts, especially in slow takeoff scenarios. A lot of forecasts, like what WFLL, mainly posit AI’s competing with each other. Consequently Molochian dynamics come into play and humans easily lose control of the future. But with these sorts of cooperative advantages, AIs are in an excellent position to not be subject to those forces and all the strategic disadvantages they bring with them. This applies even if an AI is “merely” at the human level. I could easily see an outcome that from a human perspective looks like a singleton taking over, but is in reality a collective of similar/identical AI’s working together with superhuman coordination capabilities.
I’ll also add source-code-swapping and greater transparency to the list of cooperative advantages at an AI’s disposal. Different AIs that would normally get stuck in a multipolar traps might not stay stuck for long if they can do things analogous to source code swap prisoners dilemmas.
For the most part, to the extent that we will have these advantages, it still doesn’t suggest a discontinuity; it suggests that we will be able to automate tasks with weaker / less intelligent AI systems than you might otherwise have thought.
I usually think of Part 1 of WFLL happening prior to reaching what I would call human level AI, because of these AI advantages. Though the biggest AI advantage feeding into this is simply that AI systems can be specialized to particular tasks, whereas humans become general reasoners and then apply their general reasoning to particular tasks.