By Boaz Barak and Ben Edelman

[Cross-posted on Windows on Theory blog; See also Boaz’s posts on longtermism and AGI via scaling as well as other “philosophizing” posts.]

[Disclaimer: Predictions are very hard, especially about the future. In fact, this is one of the points of this essay. Hence, while for concreteness, we phrase our claims as if we are confident about them, these are not mathematically proven facts. However we do believe that the claims below are more likely to be true than false, and, even more confidently, believe some of the ideas herein are underrated in current discussions around risks from future AI systems.]

[To the LessWrong audience: we realize this piece is stylistically different from many posts here, and is not aimed solely at regular readers, for which various terms and claims below might be very familiar. Our original impetus to write this piece was a suggestion from the organizers of the Future Fund AI worldview competition; while we are not holding our breath for any reward, we thought it would be a good idea to engage with the LessWrong audience in this discussion. This post could be described as somewhere between an ordinary collaboration and an adversarial one—the views expressed are a closer fit for Boaz's current views than Ben's.]

 

In the past, the word “computer” was used to denote a person that performs calculations. Such people were highly skilled and were crucial to scientific enterprises. As described in the book “Hidden Figures”, until the 1960s, NASA still used human computers for the space mission. However, these days a $10 calculator can instantly perform calculations beyond the capabilities of every human on earth.

On a high level, the situation in Chess and other games is similar. Humans used to be the reigning champions in Chess and Go, but have now been surpassed by computers. Yet, while the success of computers in performing calculations has not engendered fears of them “taking over the world,” the growing powers of AI systems have more people increasingly worried about their long-term implications. Some reasons why the success of AI systems such as AlphaZero in Go and Chess is more concerning than the success of calculation programs include

  1. Unlike when working with numerical computation programs, it seems that in Chess and Go humans are entirely “unnecessary.” There is no need to have a “human in the loop”. Computer systems are so powerful that no meaningful competition is possible between even the best human players and software running on commodity laptops.[1]
     
  2. Unlike the numerical algorithms used for calculations, we do not understand the inner workings of AI chess systems, especially ones trained without any hand-designed knowledge. These systems are to a large extent “black boxes,” which even their creators do not fully understand and hence cannot fully predict or control.
     
  3. Moreover, AlphaZero was trained using a paradigm known as reinforcement learning or RL (see also this book). At a high level, RL can be described as training an agent to learn a strategy (i.e., a rule to decide on a move or action based on the history of all prior ones) in order to maximize a long-term reward (e.g., “win the game”). The result is a system that is capable of executing actions that may seem wrong in the short term (e.g., sacrificing a queen) but will help achieve the long-term goal. 

 

While RL so far has had very limited success outside specific realms such as games or low-complexity settings, the success of (non-RL) deep learning systems such as GPT-3 or Dall-E in open-ended text or image generation has raised fears of future AI systems that could both act in the real world, interacting with humans, physical, and digital systems, and do so in the pursuit of long term goals that may not be “aligned” with the interests of humanity. The fear is that such systems could become so powerful that they could end up destroying much or all of humanity. We refer to the above scenario as the loss of control scenario. It is distinct from other potential risks of Artificial Intelligence, including the risks of AI being used by humans to develop more lethal weapons, better ways for repressive regimes to surveil their population or more effective ways of spreading misinformation.

In this essay, we claim that the “loss of control” scenario rests on a few key assumptions that are not justified by our current understanding of artificial intelligence research. (This doesn’t mean the assumptions are necessarily wrong—just that we don’t believe the preponderance of the evidence supports them.)  To be clear, we are not “AI skeptics” by any means. We fully believe that over the next few decades, AI will continue to make breakthrough advances, and AI systems will surpass current human performance in many creative and technical fields, including, but not limited to, software engineering, hacking, marketing, visual design, (at least some components of) scientific discovery, and more. We are also not “techno-optimists.” The world already faces risks, and even existential ones, from the actions of humans. People who have had control over nuclear weapons over the course of history include Joseph Stalin, Kim Jong-un, Vladimir Putin, and many others whose moral judgment is suspect, to say the least. Nuclear weapons are not the only way humans can and have caused suffering on a mass scale; whether it is biological, chemical, or even so-called “conventional” weapons, climate change, exploitation of resources and people, or others, humans have a long history of pain and destruction. Like any new technology, AI will be (and in fact already has been) used by humans for warfare, manipulations, and other illicit goals. These risks are real and should be studied, but are not the focus of this essay.

Our argument: an executive summary.

The loss of control scenario is typically described as a “battle” between AIs and humans, in which AIs would eventually win due to their superior abilities. However, unlike in Chess games, humans can and will use all the tools at their disposal, including many tools (e.g., code-completion engines, optimizers for protein folding, etc..) that are currently classified as “Artificial Intelligence”. So to understand the balance of power, we need to distinguish between systems or agents that have only short-term goals, versus systems that plan their own long-term strategies

The distinction above applies not just to artificial systems but also to human occupations as well. As an example, software developers, architects, engineers, or artists have short-term goals, in the sense that they provide some particular product (piece of software, design for a bridge, artwork, scientific paper) that can stand and be evaluated on its own merits. In contrast, leaders of companies and countries set long-term goals in the sense that they need to come up with a strategy that will yield benefits in the long run and cannot be assessed with confidence until it is implemented.[2] 

We already have at least partial “short-term AI”, even if not at the level of replacing e.g., human software engineers. The existence of successful “long-term AI” that can come up with strategies which are enacted over a scale of, say, years is still an open question, but for the sake of this essay we accept that assumption.

We believe that when evaluating the loss-of-control scenario, the relevant competition is not between humans and AI systems, but rather between humans aided with short-term AI systems and long-term AI systems (themselves possibly aided with short-term components). One thought experiment we have in mind is a competition between two firms: one with a human CEO, but with AI engineers and advisors, and the other a fully AI firm.

While it might seem “obvious” that eventually AI would be far superior to humans in all endeavors, including being a CEO, we argue that this is not so obviously the case. We agree that future AIs could possess superior information processing and cognitive skills - a.k.a. “intelligence” - compared to humans. But the evidence so far suggests the advantages of these skills would be much more significant in some fields than in others. We believe that this is uncontroversial - for example, it’s not far-fetched to claim that AI would make much better chess players than kindergarten teachers. Specifically, there are “diminishing returns” for superior information-processing capabilities in the context of setting longer-term goals or strategies. The long time horizon and the relevance of interactions among high numbers of agents (who are themselves often difficult to predict) make real-life large-scale systems “chaotic” in the sense that even with superior analytic abilities, they are still unpredictable (see Figure 1).

As a consequence, we believe the main fields where AI systems will yield advantages will be in short-term domains. An AI engineer will be much more useful than an AI CEO (see also Table 2). We do not claim that it would be impossible to build an AI system that can conceive and execute long-term plans; only that this would not be where AI would have a “competitive advantage”. Short-term goals that can be evaluated and graded also mesh much better with the current paradigm of training AI systems on vast amounts of data.

We believe it will be possible to construct very useful AIs with only short-term goals, and in fact that the vast majority of AI’s power will come from such short-term systems. Even if a long-term AI system is built, it will likely not have a significant advantage over humans assisted with short-term AIs. There can be many risks even from short-term AI systems, but such machines cannot by design have any long-term goals, including the goal of taking over the world and killing all humans.[3]

Perspective. Our analysis also has a lesson for AI safety research. Traditionally, approaches to mitigate the behavior of bad actors include

  • Prevention: We prevent break-ins by putting locks on our doors, we prevent hacks by securing our systems, etc… 
  • Deterrence: Another way we prevent bad actions is by ensuring that the negative consequences for these actions will outweigh benefits. This is one basis for the penal system, as well as the “mutually assured destruction” paradigm that has kept Russia and US from a nuclear war.
  • Alignment: We try to educate children and adults and socialize them to our values, so they are not motivated to pursue the actions we consider as bad.

Much of AI safety research (wrt to the “loss of control” scenario) has been focused on the third approach, with the expectation that these systems may be so powerful that prevention and deterrence will be impossible. However, it is unclear to us that this will be the case. For example, it may well be that humans, aided by short-term AI systems, could vastly expand the scope of formally verified secure systems, and so prevent hacking attacks against sensitive resources. A huge advantage of research on prevention is that it is highly relevant not just to protect against hypothetical future bad AI actors, but also against current malicious humans. Such research might greatly benefit from advances in AI code-completion engines and other tools, hence belying the notion that there is a “zero-sum game” between “AI safety” and “AI capabilities” research. 

Furthermore, one advantage of studying AI systems, as opposed to other organisms, is that we can try to extract useful modules and representations for them. (Indeed, this is already done in “transfer learning.”) Hence, it may be possible to extract useful and beneficial “short-term AI” even from long-term systems. Such restricted systems would still give most of the utility, but with less risk. Once again, increasing the capabilities of short-term AI systems will empower humans that are assisted by such systems.
 

Figure 1: Cartoon of the feasibility of predicting future events and the level of ability (i.e., cognitive skill / compute / data) required to do so (approximately) optimally. As the horizon grows, events have more inherent uncertainty and also require more skills/data to predict. However, many realistic systems are chaotic and become unpredictable at some finite horizon.[4]  At that point, even sophisticated agents cannot predict better than baseline heuristics, which require only a bounded level of skill.
 

ProfessionCognitive Score (standard deviations)Annual Earnings 
Mayors6.2 ( ≈ +0.6σ )679K SEK
Parliamentarians6.4 ( ≈ +0.7σ )802K SEK
CEOs (10-24 employees)5.8 ( ≈ +0.4σ )675K SEK
CEOs (25-249 employees)6.2 ( ≈ +0.6σ )1,046K SEK
CEOs (≥ 250 employees)6.7 ( ≈ +0.85σ )1,926K SEK
Medical Doctors7.4 ( ≈ +1.2σ )640K SEK
Lawyers and Judges6.8 ( ≈ +0.9σ )568K SEK
Economists7 ( ≈ +1σ )530K SEK
Political Scientists6.8 ( ≈ +0.9σ )513 SEK

Table 2: Cognitive scores for Swedish men in various “elite” occupations, based on Swedish army entrance examinations, taken from Dal Bó et al (Table II). Emphases ours: bold text corresponds to jobs that (in our view) require longer horizon decision-making across time or number of people. Note that despite being apparently less cognitively demanding, the “bold” professions are higher paying.

 

A digression: what is intelligence

Merriam-Webster defines intelligence as “the skilled use of reason”, “the ability to learn or understand or to deal with new or trying situations”, or “to apply knowledge to manipulate one's environment or to think abstractly.” Intelligence is similar to computation, in the sense that its main components are the ability to take in observations (aka “inputs”) and use reasoning (aka “algorithms”) to decide on actions (aka “outputs”). In fact, in the currently dominant paradigm of AI, performance is primarily determined by the amount of computation performed during learning, and AI systems consist of enormous homogeneous circuits executing a series of simple operations on (a large quantity of) inputs and learned knowledge. Bostrom (Chapter 3) defines three forms of “superintelligence”: “speed superintelligence”, “collective superintelligence” and “quality superintelligence”. In the language of computing, speed super-intelligence corresponds to clock speed of processors, while collective super-intelligence corresponds to massive parallelism. “Quality superintelligence” is not well defined, but is presumably some type of emergent phenomenon from passing some thresholds of speed and parallelism.


A fundamental phenomenon in computing is universality: there are many restricted computational models (finite state automata, context-free grammars, simply-typed lambda calculus), but once a computational model passes a certain threshold or phase transition, it becomes universal (a.k.a. “Turing complete”), and all universal models are equivalent to one another in computational power. For example, in a cellular automata, even though each cell is very restricted (can only store a constant amount of memory and process a finite rule based only on the state of its immediate neighbors), given enough cells we can simulate any arbitrarily complex machine.[5]  Once a system passes the universality transition, it is not bottlenecked any more by the complexity of an individual unit, but rather by the resources in the system as a whole.

In the animal kingdom, we seem to have undergone a similar phase transition, whereby humans are qualitatively more intelligent than any other animal or creature. It also seems to be the case that with the invention of language, the printing press, and the Internet, we (like cellular automata) are able to combine large numbers of humans to achieve feats of collective intelligence that are beyond any one individual. In particular, the fruits of the scientific revolution of the 1500-1600s increased the scale of GDP by 10,000-fold (to the extent such comparisons are meaningful) and the distance we can measure in space a trillion-fold, all with the same brains used by our hunter-gatherer ancestors (or maybe somewhat smaller ones). 

Arguably, the fact humans are far better than chimpanzees at culturally transmitting knowledge is more significant than the gap in intelligence between individuals of the two species. Ever since the development of language, the intelligence of an individual human has not been a bottleneck for the achievements of humanity. The brilliance of individuals like Newton may have been crucial for speeding up the Scientific Revolution, but there have been brilliant individuals for millennia. The crucial difference between Newton and Archimedes is not that Newton was smarter, but rather that he lived at a later time and thus was able to stand on the shoulders of more giants. As another example, a collection of humans, aided by Internet-connected computers, can do much better at pretty much any intelligence feat (including but not limited to IQ exams) than any single human. 
 

Figure 3: Measures of human progress both in terms of GDP and the scale of objects we can measure. Taken from this blog post, with the first figure from Our World in Data, and data for second figure from Terence Tao’s cosmic ladder presentation.


The “loss of control” scenario posits a second phase transition, whereby once AI systems become more powerful, they would not merely enable humans to achieve more objectives quicker but would themselves become as qualitatively superior to humans as humans are to other animals. We are suggesting an alternative future scenario, in which while AI would provide powerful new capabilities to human society that can (and unfortunately likely will) be used for ill as well as good, the AI systems themselves would not be the inevitable leaders of this society.

Indeed, our societies and firms do not currently select our leaders to be the top individuals in intellectual capacity. The evidence is very limited that “natural talent for leadership” (to the extent it exists) is as measurable and transferable as talent for chess, math, or athletics. There are many examples of leaders who have been extremely successful in one setting but failed in another which seems rather similar.[6] 

Whether or not an AI system should be considered an “individual” is a matter for debate, but regardless, it is not at all clear that such individuals would be the leaders of the society, rather than being employed in domains such as software development and scientific discovery, where their superior information-processing capabilities would provide the most competitive advantage. Bostrom (Table 8 in Chapter 6) lists several potential “cognitive superpowers” that an AI system might develop. One category is “hacking”“technology research”, and “economic productivity”. These are skills that correspond to jobs that are not in the domain of CEOs or leaders, but rather engineers, middle managers, scientists, etc. AI systems may well be able to assist or even replace such individuals, but this does not mean such systems will be the leaders of companies or countries.

Another task Bostrom considers is “intelligence amplification” which is the ability to improve AI systems. Again, it is quite possible that AI systems would help in improving other or the same AI systems, but this on its own does not imply that they would become infinitely powerful. Specifically, if indeed stronger AI would arrive through “scaling” of massive computational resources, then there would be some hard limits on the ability to improve AI’s power solely through software updates. It is not at all clear that in terms of energy efficiency, AI systems would be much better (if at all) than humans. If the gains from scaling are far more important than gains from improved algorithms/architectures, then intelligence amplification might be primarily a function of resource acquisition rather than algorithmic research.

A third task listed is “social manipulation.” Here we must admit we are skeptical. Anyone who has ever tried to convince a dog to part with a bone or a child with a toy could attest to the diminishing returns that an intelligence advantage has in such a situation. 

Finally, Boston lists the cognitive superpower of “strategizing”, which is the ability to make long-term plans to achieve distant goals. This is the point we focus on in this essay. In short, our belief is that the chaotic nature of the real world implies diminishing returns to “three-dimensional chess” strategies that are beyond the comprehension of mere humans. Hence we do not believe that this would be a domain where AI systems have a strong competitive advantage.


A thought experiment: “The AI CEO vs. the AI advisor”

Before we delve into the technical(-ish) analysis, let us consider a thought experiment. At its heart, our argument is that the power of AI systems, present and future, will not come from the ability to make long-term strategic plans (“three-dimensional chess”) but rather from the ability to produce pieces of work that can be evaluated on their own terms. In short, we believe that even if a long-term malicious AI system is constructed, it will not have an insurmountable advantage over humans that are assisted with short-term AIs. To examine this, let us imagine two possible scenarios for how future AI could assist humans in making strategic decisions, such as running a company:

 

  • In the “AI Advisor” model, leaders could use AI to come up with simulations of the impact of decisions and possibly make some suggestions. However, humans would ultimately make the decision and evaluate their results. Key for this is that an AI would be able not just to produce a recommendation for a decision but explain how this decision would lead to improvement in some interpretable metric (e.g., revenue, market share, etc..). For example, a decision might be “let’s sell this product at a loss so we can increase our market share.”
     
  • In the “AI CEO” model, AIs could use their superior powers to choose an optimal long-term strategy as opposed to an individual decision. The strategy would not be “greedy”, in the sense of a sequence of steps each making progress on measurable goals, and it would not have any compact analysis of why it is good. Also, the only way to accrue the benefits of the strategy would be to continue pursuing it in the long term. Hence users would have to trust the AI and follow its recommendations blindly. For example, think of the case in Chess where an AI figures out that the best move is to sacrifice the queen because for any one of the possible opponent’s moves, there is a countermove, and so on and so forth. The only explanation for why this strategy is a good one may consist of an exponentially big game tree up to a certain depth.

 

Our sense is that there is strong evidence that AI would be incredibly useful for making low-level decisions (i.e., optimizing objectives under constraints) once the high-level strategy was set. Indeed, by far the most exciting advances for deep learning have not been through reinforcement learning, but rather through techniques such as supervised and unsupervised learning. (With the major exception being games like Chess and Go, though even there, given the success of non-RL engines such as Stockfish versions 12 and later, it is not clear RL is needed.) There is less evidence that “AI advisors” would be useful for setting high-level strategies, but it is certainly plausible. In particular, the power of prompt-based generative models suggests that AI could be useful for generating realistic simulations that can help better convey the impact of various decisions and events. So, while “AI engineers” might be more useful than “AI advisors”, the latter might well have their role as well. 

In contrast, we believe that there is little to no evidence for the benefits of “three-dimensional chess” strategies of the type required for the “AI CEO” scenario. The real world (unlike the game of chess or even poker), involves a significant amount of unpredictability and chaos, which makes highly elaborate strategies depending on complex branching trees of moves and counter-moves far less useful. We also find it unlikely that savvy corporate boards would place blind trust in an AI CEO given that (as mentioned above) evaluation of even human CEOs tends to be controversial. 

There is an alternative viewpoint, which is that an AI CEO would basically be equivalent to a human CEO but with superhuman “intuition” or “gut feeling” that they cannot explain but somehow leads to decisions that yield enormous benefits in the long term. While this viewpoint cannot be ruled out, there is no evidence in current deep learning successes to support it. Moreover, often great CEO’s “gut feelings” are less about particular decisions, but more about the relative importance of particular metrics (e.g., prioritizing market share or user experience over short-term profits). 

In any case, even if one does not agree with our judgment of the relative likelihoods of the above scenarios, we hope that this essay will help sharpen the questions that need to be studied, as well as what lessons can we draw about them from the progress so far of AI systems.

Technical Analysis


1. Key hypotheses behind the “Loss of Control” Scenario

For the sake of the discussion below, let’s assume that at some future time there exists an artificial intelligence system that in a unified way achieves performance far superior to that achieved by all humans today across many fields. This is a necessary assumption for the “loss of control” scenario and an assumption we accept in this essay. For the sake of simplicity, below we refer to such AI systems as “powerful”.

We will also assume that powerful AI will be constructed following the general paradigm that has been so successful in the last decade of machine learning. Specifically, the system will be obtained by going through a large amount of data and computational steps to find some instantiation (a.k.a. “parameters” or “weights”) of it that optimizes some chosen objective. Depending on the choice of the objective, this paradigm includes supervised learning (“classify this image”), unsupervised learning (“predict the next token”), reinforcement learning (“win the game”), and more.


For the loss of control scenario to occur, the following two hypotheses must be true:
 

Loss-of-Control Hypothesis 1: There will exist a powerful AI that has long-term goals.

For an AI to have misaligned long-term goals, it needs to have some long-term goals in the first place. There is a question of how to define the “goals” of an AI system or even a human for that matter. In this essay, we say that an agent has a goal X if, looking retrospectively at the history of the agent’s actions, the most parsimonious explanation for its actions was that it was attempting to achieve X, subject to other constraints or objectives. For example, while chess experts often find it hard to understand why an engine such as AlphaZero makes a specific move, by the end of the game, they often understand the reasoning retrospectively and the sub-goals it was pursuing.

In our parlance, a goal is “long-term” if it has a similar horizon to goals such as “take over the world and kill all the humans” —requiring planning over large scales of time, complexity, and number of agents involved.[7]  

In contrast, we consider goals such as “win a chess game”, “come up with a plan for a bridge that minimizes cost and can carry X traffic”, or “write a piece of software that meets the requirements Y”, as short-term goals.  As another example, “come up with a mix of stocks to invest today that will maximize return next week” is a short-term goal, while “come up with a strategy for our company that will maximize our market cap over the next decade” or “come up with a strategy for our country that will maximize our GDP for the next generation” would be long-term goals. The distinction between “short-term goals AI” and “long-term goals AI” is somewhat similar to the distinction between “Tool AI” and “Agent AI” (see here). However, what we call “short-term AI” encompasses much more than “Tool AI”, and absolutely includes systems that can take actions such as driving cars, executing trading actions, and so on and so forth.

We claim that for the “loss of control” scenario to materialize, we need not only Hypothesis 1 but also the following stronger hypothesis:

Loss-of-Control Hypothesis 2: In several key domains, only AIs with long-term goals will be powerful.


By this, we mean that AIs with long-term goals would completely dominate other AIs, in that they would be much more useful for any user (or for furthering their own goals). In particular,  a country, company or organization that restricts itself to only using AIs with short term goals would be at a severe competitive disadvantage compared to one that uses AIs with long-term goals.

Why is Hypothesis 2 necessary for the “loss of control” scenario? The reason is that this scenario requires the “misaligned long-term powerful AI” to be not merely more powerful than humanity as it exists today, but more powerful than humanity in the future. Future humans will have at their disposal the assistance of short-term AIs.

 

2. Understanding the validity of the hypotheses

We now make the following claims, which we believe cast significant doubt on Hypothesis 2.


Claim 1: There are diminishing returns to information-processing skills with longer horizons.

Consider the task of predicting the consequences of a particular action in the future. In any sufficiently complex real-life scenario, the further away we attempt to predict, the more there is inherent uncertainty. For example, we can use advanced methods to predict the weather over a short time frame, but the further away the prediction, the more the system “regresses to the mean”, and the less advantage that highly complex models have over simpler ones (see Figure 4). As in meteorology, this story seems to play out similarly in macroeconomic forecasting.  In general, we expect prediction success to behave like Figure 1 below—the error increases with the horizon until it plateaus to a baseline level of some simple heuristic(s). Hence while initially highly sophisticated models can beat simpler ones by a wide margin, this advantage eventually diminishes with the time horizon.

Tetlock’s first commandment to potential superforecasters is to triage: “Don’t waste time either on “clocklike” questions (where simple rules of thumb can get you close to the right answer) or on impenetrable “cloud-like” questions (where even fancy statistical models can’t beat the dart-throwing chimp). Concentrate on questions in the Goldilocks zone of difficulty, where effort pays off the most.”  Another way to say it is that outside of the Goldilocks zone, more effort or cognitive power does not give much returns. 

 


Figure 4:  Left: Historical weather prediction accuracy data taken from a Quora answer of Mikko Strahlendorff. With technological advances, accuracy has improved significantly, but prediction accuracy sharply decays with time. Right: Figure on relative applicability of different methods from Brent Shaw. Computationally intensive numerical prediction applies in a “goldilocks zone” of days to weeks.

 

In a variety of human endeavors, it seems that the cognitive skills needed to make decisions display a similar phenomenon. Occupations involving making decisions on the mid-range horizon, such as engineering, law, and medicine, require higher cognitive skills than those requiring long-term decisions such as CEOs or Politicians (see Table 3).

One argument people make is that intelligence is not just about IQ or “booksmarts”. We do not dispute this. However, we do believe that the key potential advantage of AI systems over their human counterparts would be the ability to quickly process large amounts of information, which in humans is approximated by scores such as IQ. If that skill were key to successful leadership of companies or countries, then we would expect CEOs and leaders to come from the top 0.1% (≈ +3σ)  of the distribution of such scores. The data does not bear this out.[8] 


 

Claim 2: It may be possible to extract powerful short-term modules from long-term systems.

For Hypothesis 2 to be true, it should not be possible to take a powerful AI system with long-term goals, and extract from it modules that would be just as powerful in the key domains, but would have short-term goals. However, a nascent body of work identifies and extracts useful representations and sub-modules in deep neural networks. See, for example, this recent investigation of AlphaZero. We remark that some components of AlphaZero also inspired advances to the Stockfish Chess Engine (which is not trained using RL and involves a lot of hand-coded features), and whose latest version does in fact beat RL trained methods a-la AlphaZero.

A related issue is that a consistent theme of theoretical computer science is that verification is easier than solving or proving. Hence even a complex system could explain its reasoning to a simple verifier, even if that reasoning required a significant effort to discover. There are similar examples in human affairs: e.g., even though the discovery of quantum mechanics took thousands of years and multiple scientific revolutions, we can still teach it to undergraduates today whose brains are no better than those of the ancient Greeks. 


2.1 The impact of the deep learning paradigm on Hypothesis 2


The following claims have to do with the way we believe advanced AI systems will be constructed. We believe it is fair to assume that the paradigm of using massive data and computation to create such systems, by optimizing with respect to a certain objective, will continue to be used. Indeed, it is the success of this paradigm that has caused the rise in concerns about AI in the first place.  In particular, we want to make a clear distinction between the training objective, which the system is designed to optimize, versus the goals that the system appears to follow during its deployment.

 

Claim 3: There may be fundamental “scaling laws” governing the amount of performance AI systems can achieve as a function of the data and computational resources.

One of the original worries in the AI risk literature is the “singularity” scenario, by which an AI system continuously improves its own performance without limit. However, this assumes that a system can improve itself by rewriting its code, without requiring additional hardware resources.  If there are hard limits to what can be achieved with a certain level of resources, then such self-improvements will also hit diminishing returns. There has been significant evidence for thescaling laws” hypothesis in recent years.




Figure 5: Scaling laws as computed by Hoffman et al (“Chinchilla”), see Figure A4 there. While the scaling laws are shaped differently from those of Kaplan et al, the qualitative point we make remains the same.


 

Claim 4: When training with reinforcement learning, the gradient signal may decrease exponentially with the length of the horizon.

Consider training a system that chooses a sequence of actions, and only gets a reward after H steps (where H is known as the “horizon”). If at any step there is some probability of an action leading to a “dead end” then the chances of getting a meaningful signal decrease exponentially with H. This is a fundamental obstacle to reinforcement learning and its applicability in open-ended situations with a very large space of actions, and a non-trivial cost for any interaction. In particular, one reason AlphaZero was successful was that in games such as chess, the space of legal moves is very constrained, and in the artificial context of a game it is possible to “reset” to a particular position: that is, one can try out different actions and see what their consequences are, and then go back to the same position. This is not possible when interacting in the real world.


 As a corollary of Claim 4, we claim the following:

Claim 5: There will be powerful AI systems that are trained with short-term objective functions.

By this, we mean models that are trained on a reward/loss function that only depends on a relatively short span of actions/outputs. A canonical example of this is next-token prediction. That is, even if the eventual deployment of the model will involve it making actions and decisions over a long time horizon, its training will involve optimizing short-term rewards.

 One might think that the model's training does not matter as much, since once it is deployed in the real world, much of what it will learn will be “on the job”. However, this is not at all clear. Suppose the average worker reads/hears about 10 pages per day, which is roughly 5K tokens, leading to roughly 2M tokens per year. In contrast, future AIs will likely be trained on a trillion tokens or so, corresponding to the amount a worker will see in 5 million years! This means that while “fine-tuning” or “in context” learning can and will occur, many of the fundamental capabilities of the systems will be fixed at the time of training (as appears to be the case for pre-trained language models that are fine-tuned with human feedback).

 

If we assume that powerful AIs will be trained with short-term objectives, then Hypothesis 2 requires that (in several key domains) every such system will develop long-term goals. In fact, for the loss-of-control scenario to hold, every such system should develop more-or-less the same sort of goal (e.g., “take over the world”).

While it is certainly possible for systems that evolve from simple rules to develop complex behavior (e.g., cellular automata), for a long-term goal to consistently emerge from mere short-term training, there should be some causal relation (or at least persistent correlation)  between the long-term goal and the short-term training objective. This is because an AI system can be modeled as a maximizer of the objective on which it was trained. Thus for such a system to always pursue a particular long-term goal, that goal should be correlated with maximizing the training objective.

We illustrate this with an example. Consider an AI software developer which is trained to receive a specification of a software task (say, given by some unit tests) and then come up with a module implementing it, obtaining a reward if the module passes the tests. Now suppose that in actual deployment, the system is also writing the tests that would be used to check its future outputs. We might worry that the system would develop a “long-term” goal to maximize total reward by writing one faulty test, taking the “hit” on it, and receiving a low reward, but then getting high rewards on future tasks. However, that worry would be unfounded, since the AI software developer system is trained to maximize the reward for each task separately, as opposed to maximizing the sum of rewards over time over adaptively chosen inputs of its own making.

Indeed, this situation can already happen today. Next-token prediction models such as GPT-3 are trained on the reward of the perplexity over a single token, but when they are deployed, we typically generate a long sequence of tokens. Now consider a model that simply outputs an endless repetition of the word “blah”. The first few repetitions would get very low rewards, since they are completely unexpected, but once n is large enough (e.g. 10 or so), if you’ve already seen n “blah”s then the probability that the n+1 st word is also “blah” is very high.  So if the model were to be maximizing total reward, it may well be worth “taking the hit” by outputting a few blahs. The key point is that GPT-3 does not do that. Since it is trained on predicting the next token for human-generated (as opposed to the text generated by itself), it will optimize for this short-term objective rather than the long-term one.

We believe the example above generalizes to many other cases. An AI system trained in the current paradigm is, by default, a maximizer of the objective it was trained on, rather than an autonomous agent that pursues goals of its own design. The shorter the horizon and more well-defined the objective is, the less likely that optimizing it will lead to systems that appear to take elaborate plans to pursue far-reaching (good or bad) long-term goals. 


Summary

Given the above, we believe that while AI will continue to yield breakthroughs in many areas of human endeavor, we will not see a unitary nigh-omnipotent AI system that acts autonomously to pursue long-term goals. Concretely, even if a successful long-term AI system could be constructed, we believe that this is not a domain where AI will have a significant “competitive advantage” over humans.

Rather, based on what we know, it is likely that AI systems will have a “sweet spot” of a not-too-long horizon in which they can provide significant benefits. For strategic and long-term decisions that are far beyond this sweet spot, the superior information processing skills of AIs will give diminishing returns. (Although AIs will likely supply valuable input and analysis to the decision makers.).  An AI engineer may well dominate a human engineer (or at least one that is not aided by AI tools), but an AI CEO’s advantage will be much more muted, if any, over its human counterpart. Like our world, such a world will still involve much conflict and competition, with all sides aided by advanced technology, but without one system that dominates all others.

If our analysis holds, then it also suggests different approaches to mitigating AI risk than have been considered in the “AI safety” community. Currently, the prevailing wisdom in that community is that AI systems with long-term goals are a given, and hence the approach to mitigate their risk is to “align” these goals with human values. However, perhaps more evidence should be placed on building just-as-powerful AI systems that are restricted to short time horizons. Such systems could also be used to monitor and control other AIs, whether autonomous or directed by humans. This includes monitoring and hardening systems against hacking, detecting misinformation, and more. Regardless, we believe that more research needs to be done on understanding the internal representations of deep learning systems, and what features and strategies emerge from the training process (so we are happy that the AI safety community is putting increasing resources into “interpretability” research). There is some evidence that the same internal representations emerge regardless of the choices made in training.

There are also some technical research directions that would affect whether our argument is correct. For instance, we are interested in seeing work on the impacts of noise and unpredictability on the performance of reinforcement learning algorithms; in particular, on the relative performance of models of varying complexity (i.e. scaling laws for RL).

Acknowledgments: Thanks to Yafah Edelman for comments on an earlier version of this essay.


 

  1. ^

    During the 90s-2000s, human-engine teams were able to consistently beat engines in “advanced chess” tournaments, but no major advanced chess tournament seems to have taken place since the release of AlphaZero and the resulting jump in engine strength, presumably because the human half of each team would be superfluous.

  2. ^

    The success of a bridge does hinge on its long-term stability, but stability can be tested before the bridge is built, and coming up with measures for load-bearing and other desiderata is standard practice in the engineering profession. An AI trained using such a short-term evaluation suite as its reward function may still “overoptimize” against the metric, a la Goodhart’s Law, but this can likely be addressed with regularization techniques.

  3. ^

    It may be the case that, for subtle reasons, if we try to train an AI with only short-term goals—e.g. by training in a series of short episodes—we could accidentally end up with an AI that has long-term goals. See Claim 6 below. But avoiding this pitfall seems like an easier problem than “aligning” the goals of an AI that is explicitly meant to care about the long-term.

  4. ^

    We don’t mean that they satisfy all the formal requirements to be defined as a chaotic system; though sensitivity to initial conditions is crucial.

  5. ^

    For a nice illustration, see Sam Trajtenberg’s construction of Minecraft in Minecraft, or this construction of Life in Life.

  6. ^

    Steve Jobs at Apple vs NeXT is one such example; success and failure can themselves be difficult to distinguish even with the benefit of hindsight, as in the case of Jack Welch.

  7. ^

    For example, such planning might require setting up many companies to earn large amounts of funds, conducting successful political campaigns in several countries, constructing laboratories without being detected, etc. Some such “take-over scenarios” are listed by Bostrom, as well as Yudkowski and Urban.

  8. ^

    It is hypothetically possible that companies would be better off en masse if they hired smarter CEOs than they currently do, but given the high compensation CEOs receive this doesn’t seem like a particularly plausible equilibrium.

46

New Comment
22 comments, sorted by Click to highlight new comments since: Today at 3:49 AM

Thanks for posting, I thought this was interesting and reasonable.

Some points of agreement:

  • I think many of these are real considerations that the risk is lower than it might otherwise appear.
  • I agree with your analysis that short-term and well-scoped decisions will probably tend to be a comparative advantage of AI systems.
  • I think it can be productive to explicitly focus on  “narrow” systems (which pursue scoped short-term goals, without necessarily having specifically limited competence) and to lean heavily on the verification-vs-generation gap.
  • I think these considerations together with a deliberate decision to focus on narrowness could significnatly (though not indefinitely) postpone the point when alignment difficulties could become fatal.
  • I think that it's unrealistic for AI systems to rapidly improve their own performance without limits. Relatedly, I sympathize with your skepticism about the story of a galaxy-brained AI outwitting humanity in a game of 3 dimensional chess.

My most important disagreement is that I don’t find your objections to hypothesis 2 convincing. I think the biggest reason for this is that you are implicitly focusing on a particular mechanism that could make hypothesis 2 true (powerful AI systems are trained to pursue long-term goals because we want to leverage AI systems’ long-horizon planning ability) and neglecting two other mechanisms that I find very plausible. I’ll describe those in two child comments so that we can keep the threads separate. Out of your 6 claims, I think only claim 2 is relevant to either of these other mechanisms.

I also have some scattered disagreements throughout:

  • So far it seems extremely difficult to extract short-term modules from models pursuing long-term goals. It’s not clear how you would do it even in principle and I don’t think we have compelling examples. The AlphaZero -> Stockfish situation does not seem like a successful example to me, though maybe I'm missing something about the situation. So overall I think this is worth mentioning as a possibility that might reduce risk (alongside many others), but not something that qualitatively changes the picture.
  • I’m very skeptical about your inference from “CEOs don’t have the literal highest IQs” to “cognitive ability is not that important for performance as a CEO,” and even moreso for jumping all the way to “cognitive ability is not that important for long-term planning.” I think that (i) competent CEOs are quite smart even if not in the tails of the IQ distribution, (ii) there are many forms of cognitive ability which are only modestly correlated, and so the tails come apart, (iii) there are huge amounts of real-world experience that drive CEO performance beyond cognitive ability, (iv) CEO selection is not perfectly correlated with performance. Given all of that, I think you basically can’t get any juice out of this data. If anything I would say the high compensation of CEOs, their tendency to be unusually smart, and skill transferability across different companies seem to provide some evidence that CEO cognitive ability has major effects on firm performance (I suspect there is an economics literature investigating this claim). Overall I thought this was the weakest point of the article.
  • While I agree there are fundamental computational limits to performance, I don’t think they qualitatively change the picture about the singularity. This is ultimately a weedsy quantitative question and doesn’t seem central to your point so I won't get into it, but I’d be happy to elaborate if it feels like an important disagreement. I also don’t think the scaling laws you cite support your claim; ultimately the whole point is that the (compute vs performance) curves tend to fall with further R&D.
  • I would agree with the claim “more likely than not, AI systems won’t take over the world.” But I don’t find <50% doom very comforting! Indeed my own estimate is more like 10-20% (depending on what we are measuring) but I still consider this a plurality of total existential risk and a very appealing thing to work on. Overall I think most of the considerations you raise are more like quantitative adjustments to these probabilities, and so a lot depends on what is in fact baked in or how you feel about the other arguments on offer about AI takeover (in both directions).
  • I think you are greatly underestimating the difficulty of deterrence and prevention. If AI systems are superhuman for short-horizon tasks, it seems like humans would become reliant on AI help to prevent or contain bad behavior by other AIs. But if there are widespread alignment problems, then the AI systems charged with defending humans may instead join in to help disempower humanity. Without progress on alignment it seems like we are heading towards an increasingly unstable word. The situation is quite different from preventing or deterring human “bad actors;” amongst humans the question is how to avoid destructive negative-sum behavior, whereas in the hypothetical situation you are imagining vast numbers of AIs who are doing almost all the work and don't care about human flourishing, yet somehow trying to structure society so that it nevertheless leads to human flourishing.

Mechanism 2: deceptive alignment

Suppose that during training my AI system had some arbitrary long-term goal. Many long-term goals would be best-served if the deployed AI system had that same goal. And so my AI is motivated to get a low loss, so that gradient descent won’t change its goals.

As a result, a very wide range of long-term goals will lead to competent loss-minimizing behavior. On the other hand, there is a very narrow range of short-term goals that lead to competent loss-minimizing behavior: “minimize the loss.”

So gradient descent on the short-term loss function can easily push towards long-term goals (in fact it would both push towards the precise short-term goals that result in low loss and arbitrary long-term goals, and it seems like a messy empirical question which one you get). This might not happen early in training, but eventually our model is competent enough to appreciate these arguments and perhaps for it to be extremely obvious to it that it should avoid taking actions that would be penalized by training.

It doesn’t seem like there are any behavioral checks we can do to easily push gradient descent back in the other direction, since an agent that is trying to get a low loss will always just adopt whatever behavior is best for getting a low loss (as long as it thinks it is on the training distribution).

This all is true even if my AI has subhuman long-horizon reasoning. Overall my take is maybe that there is a 25% chance that this becomes a serious issue soon enough to be relevant to us and that is resistant to simple attempts to fix it (though it’s also possible we will fail to even competently implement simple fixes). I expect to learn much more about this as we start engaging with AI systems intelligent enough for it to be a potential issue over the next 5-10 years.

This issue is discussed here. Overall I think it’s speculative but plausible.

I agree that this sort of deceptive misalignment story is speculative but a priori plausible. I think it's very difficult to reason about these sorts of nuanced inductive biases without having sufficiently tight analogies to current systems or theoretical models; how this will play out (as with other questions of inductive bias) probably depends to a large extent on what the high-level structure of the AI system looks like. Because of this, I think it's more likely than not that our predictions about what these inductive biases will look like are pretty off-base. That being said, here are the first few specific reasons to doubt the scenario which come to mind right now:

  1. If the system is modular, such that the part of the system representing the goal is separate from the part of the system optimizing the goal, then it seems plausible that we can apply some sort of regularization to the goal to discourage it from being long term. It's imaginable that the goal is a mesa-objective which is mixed in some inescapably non-modular way with the rest of the system, but then it would be surprising to me if the system's behavior could really best be best characterized as optimizing this single objective; as opposed to applying a bunch of heuristics, some of which involve pursuing mesa-objectives and some of which don't fit into that schema—so perhaps framing everything the agent does in terms of objectives isn't the most useful framing (?).
  2. If an agent has a long-term objective, for which achieving the desired short-term objective is only instrumentally useful, then in order to succeed the agent needs to figure out how to minimize the loss by using its reasoning skills (by default, within a single episode). If, on the other hand, the agent has an appropriate short-term objective, then the agent will learn (across episodes) how to minimize the loss through gradient descent. I expect the latter scenario to typically result in better loss for statistical reasons, since the agent can take advantage of more samples. (This would be especially clear if, in the training paradigm of the future, the competence of the agent increases during training.)

(There's also the idea of imposing a speed prior; not sure how likely that direction is to pan out.)

Perhaps most crucially, for us to be wrong about Hypothesis 2, deceptive misalignment needs to happen extremely consistently. It's not enough for it to be plausible that it could happen often; it needs to happen all the time.

If the system is modular, such that the part of the system representing the goal is separate from the part of the system optimizing the goal, then it seems plausible that we can apply some sort of regularization to the goal to discourage it from being long term.

What kind of regularization could this be?  And are you imagining an AlphaZero-style system with a hardcoded value head, or an organically learned modularity?

Perhaps most crucially, for us to be wrong about Hypothesis 2, deceptive misalignment needs to happen extremely consistently. It's not enough for it to be plausible that it could happen often; it needs to happen all the time.

I think the situation is much better if deceptive alignment is inconsistent. I also think that's more likely, particularly if we are trying.

That said, I don't think the problem goes away completely if deceptive alignment is inconsistent. We may still have limited ability to distinguish deceptively aligned models from models that are trying to optimize reward, or we may find that models that are trying to optimize reward are unsuitable in practice (e.g. because of the issues raised in mechanism 1) and so selecting for things that works means you are selecting for deceptive alignment.

Mechanism 1: Shifting horizon length in response to short-horizon tampering

Suppose I want my AI to write good code (say to help me run my business). The AI understands a lot about how to write code, how servers work, and how users behave, learned entirely from quick feedback and experimentation. Let’s say it has a human-level or even subhuman understanding of the overall business and other long-term planning.

(This example may seem a bit silly if you imagine a software-writing AI in isolation, but you should think of the same story playing out all across an economy in parallel as AI systems take on an extremely wide range of tasks.)

How do I train that system to use its understanding to write good code? Here are two simple options:

  1. Process-based: Look at the AI’s code, have the AI explain why it made these decisions, and evaluate everything on paper.
  2. Outcomes-based: Run the code, monitor resource usage, see what users say in the first hour after deployment.

Process-based feedback potentially handicaps my AI (even if it is only superhuman on short-horizon tasks). It’s not clear how large this advantage is, but I think our experience in practice is that “actually run your engineer’s code” is an extremely helpful technique for evaluating it in practice, and it becomes more important the better your engineers are and the less able you are to evaluate decisions they made.

So without some kind of technical progress I’m afraid we may often be pushed to use outcomes-based feedback to make our systems work better.

Unfortunately outcomes-based feedback creates an adversarial interaction between me and my AI. In addition to selecting for AIs that write good code, I’m selecting for AIs that use their short-horizon abilities to write software that covers up evidence of trouble and tampers with logs, that fakes or destroys user reports or manipulates users, and that generally messes with every mechanism we try to use to understand what’s going on. (Depending on exactly what goal the system internalized, it might also be motivated to write code that directly tampers with data fed back into the ML training process.)

Maybe we can make all of those things impossible with good enough security, so that the only way for code to look good is to actually be good. But now we are setting up a larger-scale, persistent conflict between humans and the AI systems they delegate work to. And many different AI systems could potentially all simultaneously achieve their separate short-term tasks by defecting and undermining human evaluations, making it harder to use AI evaluators to reduce the risk of tampering (or creating an increasingly unstable situation if we try to go that route).

I think small versions of sensor tampering are likely to happen and are not a big deal. I’m scared about the world where this kind of failure becomes a big pain and seriously impacts the usefulness of AI. Maybe I’d wildly guess a 40% chance that we end up with a significant problem like this if we keep building ML systems using roughly the same techniques we use today (and that those problems arise soon enough to be relevant).

There are many good things we could do to fix that problem, and in some sense it would be great news for AI alignment since we’d have a concrete technical problem to iterate on.

But there is also one very bad way we could fix this problem. We could notice incidents of tampering much later, e.g. by talking to users out-of-bound or noticing we aren’t getting return traffic or seeing that resource usage measurements were clearly faked. Then we can label those incidents as examples of wha not to do and throw that data back into the training process.

This will quickly select against policies that do this kind of short-term tampering, but it could so in two ways:

  • The AI learned to not to tamper with our measurements.
  • The AI learned to not to tamper with our measurements in any way we’d catch later.

In the second case, we’ve now created an AI with long-term goals even though all we really wanted was a short-term task, and we have a similar adversarial dynamic at a larger scale. And even if the AI has merely human-level competence at long-horizon tasks, it will still try to use its short-term competencies to prevent us from ever detecting and correcting its mistakes. If we keep training out every problem at a scale that we can correct, we will eventually be left with total failures that we can’t correct (e.g. because AI systems have permanently disempowered us).

I think it’s best to view this as a kind of overfitting: we wanted to get an AI that doesn’t do anything bad, but if we train on “did we eventually notice that it did something ad?” then we will end up with a system that is overfit to that objective. And just like with overfitting, you could also imagine it happening without explicitly training on the offending data. If 5% of AI systems have long-term goals and 95% have short-term goals, you could end up with the 95% consistently behaving badly by taking short-term opportunities to tamper with our measurements, and so we would select for the 5% with long-term goals.

My main objection to this misalignment mechanism is that it requires people/businesses/etc. to ignore the very concern you are raising. I can imagine this happening for two reasons:

  1. A small group of researchers raise alarm that this is going on, but society at large doesn't listen to them because everything seems to be going so well. This feels unlikely unless the AIs have an extremely high level of proficiency in hiding their tampering, so that the poor performance on the intended objective only comes back to bite the AI's employers once society is permanently disempowered by AI. Nigh-infallibly covering up tampering sounds like a very difficult task even for an AI that is super-human. I would expect at least some of the negative downstream effects of the tampering to slip through the cracks and for people to be very alarmed by these failures.
  2. The consensus opinion is that your concern is real, but organizations still rely on outcome-based feedback in these situations anyway because if they don't they will be outcompeted in the short term by organizations that do. Maybe governments even try to restrict unsafe use of outcome-based feedback through regulation, but the regulations are ineffective. I'll need to think about this scenario further, but my initial objection is the same as my objection to reason 1: the scenario requires the actual tampering that is actually happening to be covered up so well that corporate leaders etc. think it will not hurt their bottom line (either through direct negative effects or through being caught by regulators) in expectation in the future.

Which of 1 and 2 do you think is likely? And can you elaborate on why you think AIs will be so good at covering up their tampering (or why your story stands up to tampering sometimes slipping through the cracks)?

Finally, if there aren't major problems resulting from the tampering until "AI systems have permanently disempowered us", why should we expect problems to emerge afterwards, unless the AI systems are cooperating / don't care about each other's tampering?

(Am I right that this is basically the same scenario you were describing in this post? https://www.alignmentforum.org/posts/AyNHoTWWAJ5eb99ji/another-outer-alignment-failure-story)

A small group of researchers raise alarm that this is going on, but society at large doesn't listen to them because everything seems to be going so well.

Arguably this is already the situation with alignment. We have already observed empirical examples of many early alignment problems like reward hacking. One could make an argument that looks something like "well yes but this is just in a toy environment, and it's a big leap to it taking over the world", but it seems unclear when society will start listening. In analogy to the AI goalpost moving problem ("chess was never actually hard!"), in my model it seems entirely plausible that every time we observe some alignment failure it updates a few people but most people remain un-updated. I predict that for a large set of things currently claimed will cause people to take alignment seriously, most of them will either be ignored by most people once they happen, or never happen before catastrophic failure.

We can also see analogous dynamics in i.e climate change, where even given decades of hard numbers and tangible physical phenomena large amounts of people (and importantly, major polluters) still reject its existence, many interventions are undertaken which only serve as lip service (greenwashing), and all of this would be worse if renewables were still economically uncompetitive.

I expect the alignment situation to be strictly worse because a) I expect the most egregious failures to only come shortly before AGI, so once evidence as robust as climate change (i.e literally catching AIs red handed trying and almost succeeding at taking over the world), I estimate we have anywhere between a few years and negative years left b) the space of ineffectual alignment interventions is far larger and harder to distinguish from real solutions to the underlying problem c) in particular, training away failures in ways that don't solve the underlying problems (i.e incentivizing deception) is an extremely attractive option and there does not exist any solution to this technical problem, and just observing the visible problems disappear is insufficient to distinguish whether the underlying problems are solved d) 80% of the tech for solving climate change basically already exists or is within reach, and society basically just has to decide that it cares, and the cost to society is legible. For alignment, we have no idea how to solve the technical problem, or even how that solution will vaguely look. This makes it a harder sell to society, e) the economic value of AGI vastly outweighs the value of fossil fuels, making the vested interest substantially larger, f) especially due to deceptive alignment, I expect actually-aligned systems to be strictly more expensive than unaligned systems; the cost will be more than just a fixed % more money, but also cost in terms of additional difficulty and uncertainty, time to market disadvantage, etc.

Thanks for laying out the case for this scenario, and for making a concrete analogy to a current world problem! I think our differing intuitions on how likely this scenario is might boil down to different intuitions about the following question:

To what extent will the costs of misalignment be borne by the direct users/employers of AI?

Addressing climate change is hard specifically because the costs of fossil fuel emissions are pretty much entirely borne by agents other than the emitters. If this weren't the case, then it wouldn't be a problem, for the reasons you've mentioned!

I agree that if the costs of misalignment are nearly entirely externalities, then your argument is convincing. And I have a lot of uncertainty about whether this is true. My gut intuition, though, is that employing a misaligned AI is less like "emitting CO2 into the atmosphere" and more like "employing a very misaligned human employee" or "using shoddy accounting practices" or "secretly taking sketchy shortcuts on engineering projects in order to save costs"—all of which yield serious risks for the employer, and all of which real-world companies take serious steps to avoid, even when these steps are costly (with high probability, if not in expectation) in the short term.

We have already observed empirical examples of many early alignment problems like reward hacking. One could make an argument that looks something like "well yes but this is just in a toy environment, and it's a big leap to it taking over the world", but it seems unclear when society will start listening.

I expect society (specifically, relevant decision-makers) to start listening once the demonstrated alignment problems actually hurt people, and for businesses to act once misalignment hurts their bottom lines (again, unless you think misalignment can always be shoved under the rug and not hurt anyone's bottom line). There's lots of room for this to happen in the middle ground between toy environments and taking over the world (unless you expect lightning-fast takeoff, which I don't).

I expect that the key externalities will be borne by society. The main reason for this is I expect deceptive alignment to be a big deal. It will at some point be very easy to make AI appear safe, by making it pretend to be aligned, and very hard to make it actually aligned. Then, I expect something like the following to play out (this is already an optimistic rollout intended to isolate the externality aspect, not a representative one):

We start observing alignment failures in models. Maybe a bunch of AIs do things analogous to shoddy accounting practices. Everyone says "yes, AI safety is Very Important". Someone notices that when you punish the AI for exhibiting bad behaviour with RLHF or something the AI stops exhibiting bad behaviour (because it's pretending to be aligned). Some people are complaining that this doesn't actually make it aligned, but they're ignored or given a token mention. A bunch of regulations are passed to enforce that everyone uses RLHF to align their models. People notice that alignment failures decrease across the board. The models don't have to somehow magically all coordinate to not accidentally reveal deception, because even in cases where models fail in dangerous ways people chalk this up to the techniques not being perfect, but they're being iterated on, etc. Heck, humans commit fraud all the time and yet it doesn't cause people to suddenly stop trusting everyone they know when a high profile fraud case is exposed. And locally there's always the incentive to just make the accounting fraud go away by applying Well Known Technique rather than really dig deep and figuring out why it's happening. Also, a lot of people will have vested interest in not having the general public think that AI might be deceptive, and so will try to discredit the idea as being fringe. Over time, AI systems control more and more of the economy. At some point they will control enough of the economy to cause catastrophic damage, and a treacherous turn happens.

At every point through this story, the local incentive for most businesses is to do whatever it takes to make the AI stop committing accounting fraud or whatever, not to try and stave off a hypothetical long term catastrophe. A real life example that this is analogous to is antibiotic overuse.

This story does hinge on "sweeping under the rug" being easier than actually properly solving alignment, but if deceptive alignment is a thing and is even moderately hard to solve properly then this seems very likely the case.

I expect society (specifically, relevant decision-makers) to start listening once the demonstrated alignment problems actually hurt people

I predict that for most operationalizations of "actually hurt people", the result is that the right problems will not be paid attention to. And I don't expect lightning fast takeoff to be necessary. Again, in the case of climate change, which has very slow "takeoff", millions of people are directly impacted, and yet governments and major corporations move very slowly and mostly just say things about climate change mitigation being Very Important and doing token paper straw efforts. Deceptive alignment means that there is a very attractive easy option that makes the immediate crisis go away for a while.

But even setting aside the question of whether we should even expect to see warning signs, and whether deceptive alignment is a thing, I find it plausible that even the response to a warning sign that is as blatantly obvious as possible (an AI system tries to take over the world, fails, kills a bunch of people in the process) just results in front page headlines for a few days, some token statements, a bunch of political squabbling between people using the issue as a proxy fight for the broader "tech good or bad" narrative and a postmortem that results in patching the specific things that went wrong without trying to solve the underlying problem. (If even that; we're still doing gain of function research on coronaviruses!)

Thank you for the insightful comments!! I've added thoughts on Mechanisms 1 and 2 below. Some reactions to your scattered disagreements (my personal opinions; not Boaz's):

  1. I agree that extracting short-term modules from long-term systems is more likely than not to be extremely hard. (Also that we will have a better sense of the difficulty in the nearish future as more researchers work on this sort of task for current systems.)
  2. I agree that the CEO point might be the weakest in the article. It seems very difficult to find high-quality evidence about the impact of intelligence on long-term strategic planning in complex systems, and this is a major source of my uncertainty about whether our thesis is true. Note that even if making CEOs smarter would improve their performance, it may still be the case that any intelligence boost is fully substitutable by augmentation with advanced short-term AI systems.
  3. From published results I've seen (e.g. comparison of LSTMs vs Transformers in figure 7 of Kaplan et al., effects of architecture tweaks in other papers such as this one), architectural improvements (R&D) tend to have only a minimal effect on the exponent of scaling power laws; so the differences in the scaling laws could hypothetically be compensated for by increasing compute by a multiplicative constant. (Architecture choice can have a more significant effect on factors like parallelizability and stability of training.) I'm very curious whether you've seen results that suggest otherwise (I wouldn't be surprised if this were the case, the examples I've seen are very limited, and I'd love to see more extensive studies), or whether you have more relevant intuition/evidence for there being no "floor" to hypothetically achievable scaling laws.
  4. I agree that our argument should result in a quantitative adjustment to some folk's estimated probability of catastrophe, rather than ruling out catastrophe entirely, and I agree that figuring out how to handle worst-case scenarios is very productive.
  5. When you say "the AI systems charged with defending humans may instead join in to help disempower humanity", are you supposing that these systems have long-term goals? (even more specifically, goals that lead them to cooperate with each other to disempower humanity?)

Given all of that, I think you basically can’t get any juice out of this data. If anything I would say the high compensation of CEOs, their tendency to be unusually smart, and skill transferability across different companies seem to provide some evidence that CEO cognitive ability has major effects on firm performance (I suspect there is an economics literature investigating this claim).

There's a few, for example the classic "Are CEOs Born Leaders?" which uses the same Swedish data and finds a linear relationship of cognitive ability with both log company assets and log CEO pay, though it also concludes that the effect isn't super large. The main reason there aren't more is that we generally don't have good cognitive data on most CEOs. (There are plenty of studies looking at education attainment or other proxies.) You can see this trend in the Dal Bo et al Table cited in the main post as well.

(As an aside, I'm a bit worried about the Swedish dataset, since the cognitive ability of Swedish large-firm CEOs is lower than Herrnstein and Murray (1996)'s estimated cognitive ability of 12.9 million Americans in managerial roles. Maybe something interesting happens with CEOs in Sweden?)

It is very well established that certain CEOs are consistently better than others, i.e. CEO level fixed effects matter significantly to company performance across a broad variety of outcomes. 

IIUC the thesis of this article rest on several interrelated claims:

  1. Long-term planning is not useful because of chaos
  2. Short-term AIs have no alignment problem
  3. Among humans, skill is not important for leadership, beyond some point
  4. Human brains have an advantage w.r.t. animals because of "universality", and any further advantage can only come from scaling with resources.

I wish to address these claims one by one.

Claim 1

This is an erroneous application of chaos theory IMO. The core observation of chaos theory is, that in many dynamical systems with compact phase space, any distribution converges (in the Kantorovich-Rubinstein sense) to a unique stationary distribution. This means that small measurement errors lead to large prediction errors, and in the limit no information from the initial condition remains.

However, real-world dynamical systems are often not compact in the relevant approximation. In particular, acquisition of resources and development of new technologies are not bounded from above on a relevant scale. Indeed, trends in GDP growth and technological progress continue over long time scales and haven't converged, so far, to a stationary distribution. Ultimately, these quantities are also bounded for physical / information-theoretic / complexity-theoretic reasons, but since humanity is pretty far from saturating them, this leaves ample room for AI to have a long-term planning advantage over humanity.

Claim 2

Although it is true that, for sufficiently short-term planning horizons, AIs have less incentives to produce unintended consequences, problems remain.

One problem is that some tasks are very difficult to specify. For example, suppose that a group of humans armed with short-term AIs is engaged in cyberwarfare against a long-term AI. Then, even if every important step in the conflict can be modeled as short-term optimization, specifying the correct short-term goal can be a non-trivial task (how do you define "to hack" or "to prevent from hacking"?) that humans can't easily point their short-term AI towards.

Moreover, AIs trained on short-term objectives can still display long-term optimization out-of-distribution. This is because a long-term optimizer that is smart enough to distinguish between training and deployment can behave according to expectations during training while violating them as much as it wants when it's either outside of training or the correcting outer loop is too slow to matter.

Claim 3

This claim flies so much in the face of common sense (is there no such thing as business acumen? charisma? military genius?) that it needs a lot more supporting evidence IMO. The mere fact that IQs of e.g. CEOs are only moderately above average and not far above average only means that IQ stops to be a useful metric at that range, since beyond some point, different people have cognitive advantages in different domains. I think that, as scientists, we need to be careful of cavalierly dismissing the sort of skills we don't have.

As to the skepticism of the authors about social manipulation, I think that anyone who studied history or politics can attest that social manipulation has been used, and continues to be used, with enormous effects. (Btw, I think it's probably not that hard to separate a dog from a bone or child from a toy if you're willing to e.g. be completely ruthless with intimidation.)

Claim 4

While it might be true that there is a sense in which human brains are "qualitatively optimal", this still leaves a lot of room for quantitative advantage, similar to how among two universal computers, one can be vastly more efficient than the other for practical purposes. As a more relevant analogy, we can think of two learning algorithms that learn the same class of hypotheses while still having a significant difference in computational and/or sample efficiency. In the limit of infinite resources and data, both algorithms converge to the same results, but in practice one still has a big advantage over the other. While undoubtedly there are hard limits to virtually every performance metric, there is no reason to believe evolution brought human brains anywhere near those limits. Furthermore, even if "scaling with resources" is the only thing that matters, the ability of AI to scale might be vastly better than the ability of humans to scale because of communication bandwidth bottlenecks between humans, not to mention the limited trust humans have towards one another (as opposed to large distributed AI systems, or disparate AI systems that can formally verify each other's trustworthiness).

Hi Vanessa,

Let me try to respond (note the claim numbers below are not the same as in the essay, but rather as in Vanessa's comment):

Claim 1: Our claim is that one can separate out components - there is the predictable component which is non stationary, but is best approximated with a relatively simple baseline, and the chaotic component, which over the long run is just noise.In general, highly complex rules are more sensitive to noise (in fact, there are theorems along these lines in the field of Analysis of Boolean Functions), and so in the long run, the simpler component will dominate the accuracy. 

 

Claim 2: Hacking is actually a fairly well-specified endeavor. People catalog, score, and classify security vulnerabilities. To hack would be to come up with a security vulnerability, and exploit code, which can be verified. Also, you seem to be envisioning a long-term AI that is then fine-tuned on a short-term task, but how did it evolve these long-term goals in the first place?

 

Claim 3: I would not say that there is no such thing as talent in being a CEO or presidents. I do however believe that the best leaders have been some combination of their particular characteristics and talents, and the situation they were in. Steve Jobs has led Apple to become the largest company in the world, but it is not clear that he is a "universal CEO" that would have done as good in any company (indeed he failed with NeXT). Similarly,  Abraham Lincoln is typically ranked as the best U.S. president by historians, but again I think most would agree that he fit well the challenge that he had to face, rather than being someone that would have just as well handled the cold war or the 1970s energy crisis. Also, as Yafah points elsewhere here, for people to actually trust an AI with being the leader of a company or a country, it would need to not just be as good as humans or a little better, but better by a huge margin.  In fact, most people's initial suspicion is that AIs (or even humans that don't look like them) is not "aligned" with their interests, and if you don't convince them otherwise, their default would be to keep them from positions of power.

 

Claim 4: The main point is that we need to measure the powers of a system as a whole, not compare the powers of an individual human with an individual AI.  Clearly, if you took a human, made their memory capacity 10 times bigger, and made their speed 10 times faster, then they could do more things. But we are comparing with the case that humans will be assisted with short-term AIs that would help them in all of the tasks that are memory and speed intensive.

Thanks for the responses Boaz!

Our claim is that one can separate out components - there is the predictable component which is non stationary, but is best approximated with a relatively simple baseline, and the chaotic component, which over the long run is just noise.In general, highly complex rules are more sensitive to noise (in fact, there are theorems along these lines in the field of Analysis of Boolean Functions), and so in the long run, the simpler component will dominate the accuracy.

I will look into analysis of boolean functions, thank you. However, unless you want to make your claim more rigorous, it seems suspect to me.

In reality, there are processes happening simultaneously on many different timescales, from the microscopic to the cosmological. And, these processes are coupled, so that the current equilibrium of each process can be regarded as a control signal for the higher timescale processes. This means we can do long-term planning by starting from the long timescales and back-chaining to short timescales, like I began to formalize here.

So, while eventually the entire universe reaches an equilibrium state (a.k.a. heat-death), there is plenty of room for long-term planning before that.

Hacking is actually a fairly well-specified endeavor. People catalog, score, and classify security vulnerabilities. To hack would be to come up with a security vulnerability, and exploit code, which can be verified.

Yeeees, it does seem like hacking is an especially bad example. But even in this example, my position is quite defensible. Yes, theoretically you can formally specify the desired behavior of the code and verify that it always happens. But, there are two problems with that: First, for many realistic software system, the formal specification would require colossal effort. Second, the formal verification is only as good as the formal model. For example, if the attacker found a hardware exploit, while your model assumes idealized behavior for the hardware, the verification doesn't help. And, it domains outside software the situation is much worse: how do you "verify" that your biological security measures are fool-proof, for example?

Also, you seem to be envisioning a long-term AI that is then fine-tuned on a short-term task, but how did it evolve these long-term goals in the first place?

When you're selecting for success on a short-term goal you might inadvertently produce a long-term agent (which, on the training distribution, is viewing the short-term goal as instrumental for its own goals), just like how evolution was selecting for genetic fitness but ended up producing agents with many preferences unrelated to that. More speculatively, there might be systematic reasons for such agents to arise, for example if good performance in the real-world requires physicalist epistemology which comes with inherent "long-terminess".

I would not say that there is no such thing as talent in being a CEO or presidents. I do however believe that the best leaders have been some combination of their particular characteristics and talents, and the situation they were in. Steve Jobs has led Apple to become the largest company in the world, but it is not clear that he is a "universal CEO" that would have done as good in any company (indeed he failed with NeXT).

This sounds like a story you can tell about anything. "Yes, such-and-such mathematician proved a really brilliant theorem A, but their effort to make progress in B didn't amount to much." Obviously, real-world performance depends on circumstances and not only on talent. This is doubly true in a competitive setting, where other similarly talented people are working against you. Nevertheless, a sufficiently large gap in talent can produce very lopsided outcomes.

Also, as Yafah points elsewhere here, for people to actually trust an AI with being the leader of a company or a country, it would need to not just be as good as humans or a little better, but better by a huge margin. In fact, most people's initial suspicion is that AIs (or even humans that don't look like them) is not "aligned" with their interests, and if you don't convince them otherwise, their default would be to keep them from positions of power.

First, it is entirely possible the AI will be better by a huge margin, because like with most things, there's no reason to believe evolution brought us anywhere near the theoretical optimum on this. (Yes, there was selective pressure, but no amount of selective pressure allowed evolution to invent spaceships, or nuclear reactors, or even the wheel.) Second, what if the AI poses as a human? Or, what if the AI uses a human as a front while pulling the strings behind the scenes? There will be no lack of volunteers to work as such a front, if in the short-term them it brings them wealth and status. Also, ironically, the more successful AI risk skeptics are at swaying public opinion, the easier the AIs job is and the weaker their argument becomes.

The main point is that we need to measure the powers of a system as a whole, not compare the powers of an individual human with an individual AI. Clearly, if you took a human, made their memory capacity 10 times bigger, and made their speed 10 times faster, then they could do more things. But we are comparing with the case that humans will be assisted with short-term AIs that would help them in all of the tasks that are memory and speed intensive.

Alright, I can see how the "universality" argument makes sense if you believe that "human + short-term AI = scaled-up human". The part I doubt is that this equation holds for any easy-to-specify value of "short-term AI".

Hi Vanesssa,

Perhaps given my short-term preference, it's not surprising that I find it hard to track very deep comment threads, but let me just give a couple of short responses.

I don't think the argument on hacking relied on the ability to formally verify systems. Formally verified systems could potentially skew the balance of power to the defender side, but even if they don't exist, I don't think balance is completely skewed to the attacker. You could imagine that, like today, there is a "cat and mouse" game, where both attackers and defenders try to find "zero day vulnerabilities" and exploit (in one case) or fix (in the other). I believe that in the world of powerful AI, this game would continue, with both sides having access to AI tools, which would empower both but not necessarily shift the balance to one or the other. 

I think the question of whether a long-term planning agent could emerge from short-term training is a very interesting technical question!  Of course we need to understand how to define "long term" and "short term" here.  One way to think about this is the following: we can define various short-term metrics, which are evaluable using information in the short-term, and potentially correlated with long-term success. We would say that a strategy is purely long-term if it cannot be explained by making advances on any combination of these metrics.

I don't think the argument on hacking relied on the ability to formally verify systems. Formally verified systems could potentially skew the balance of power to the defender side, but even if they don't exist, I don't think balance is completely skewed to the attacker.

My point was not about the defender/attacker balance. My point was that even short-term goals can be difficult to specify, which undermines the notion that we can easily empower ourselves by short-term AI.

Of course we need to understand how to define "long term" and "short term" here. One way to think about this is the following: we can define various short-term metrics, which are evaluable using information in the short-term, and potentially correlated with long-term success. We would say that a strategy is purely long-term if it cannot be explained by making advances on any combination of these metrics.

Sort of. The correct way to make it more rigorous, IMO, is using tools from algorithmic information theory, like I suggested here.

Hi, thanks both for writing this - I enjoyed it.

  1. I'd be interested in your thoughts on how we can do this:
    > However, perhaps more [emphasis] should be placed on building just-as-powerful AI systems that are restricted to short time horizons.

I can share some of my thoughts first, and would be keen to hear (both/either of) yours.

  • It's worth saying up front that I also think this is a very productive direction, and that your post lays out a good case for why.
  • Here's one salient baseline strategy, and a corresponding failure mode: At each point in time t, where is some time horizon h where AIs can pursue goals over horizon h. At each point in time, (social-impact-minded) AI companies aim to build "short-term goal" systems, which operate at horizon h, but not longer.
    • Note that this seems very natural, and also exactly matches what one might expect a purely profit- or prestige-driven company to do.
  • However, if h turns out to steadily increase over time (as in the straight-line extrapolation referenced below), then this leaves us in a difficult position.
    • Furthermore, this seems to leave us at the mercy of unknown empirical questions about deep learning. It doesn't seem we have improved our chances relative to the baseline of "do the easiest thing at each point in time".
  • So from a "differential progress" perspective, a more helpful research strategy seems to be: fix a task with some horizon h_1, then try to solve this task using only systems optimized over horizon h_2 < h_1.
    • This framing also possibly highlights two additional difficulties: (1) technically, end-to-end optimization has been quite effective for many DL tasks and (2) sociologically, the DL community has a tremendous aesthetic preference towards end-to-end approaches (which also translates into approaches and infra which favor end-to-end approaches), which makes it harder to gain widespread adoption for other approaches. Also agreed there are many offsetting factors like interpretability, control, etc. which you mention.
    • This suggests empirical angles similar to the one described [here](https://ought.org/updates/2022-04-06-process) by Ought.
  • I'd be very interested in how you think about this research direction, and particularly interested if you think there are other/complementary research directions which improve our chances of ending up with short time horizon AIs.

2. I understand this matches up with your core point, but to check understanding and confirm agreement - It seems far from certain that so-called "short-term goal" AIs will dominate, and given these uncertainties, it  

  • I would guess you are both somewhat more optimistic about "short-term goal AIs" than I am (in most discussions, I normally find myself arguing for competitiveness of short-term goal AIs, so it's a nice change-of-perspective for me!). But I imagine(?) we might have similar views that:
    • So long as p("short-term AIs dominate") is not very close to 1, this leaves substantial risk.
    • So long as p("short-term AIs dominate") is not very close to 1, then there is reasonable room for dedicated efforts to push this probability up (or down).
  • There are many reasons this seems uncertain, but to spell out one: As you correctly point out, the applications where DL is useful right now (to the extent there are any) are predominantly short-term ones. But it also seems that the natural trend over time would be for AIs to move to competency on increasingly broad tasks in the future, and so the current situation doesn't provide much evidence whether to expect this straight-line extrapolation vs. a Goldilocks effect you describe.

3. As a final point, regarding this: 

Loss-of-Control Hypothesis 2: In several key domains, only AIs with long-term goals will be powerful.
...
Why is Hypothesis 2 necessary for the “loss of control” scenario? The reason is that this scenario requires the “misaligned long-term powerful AI” to be not merely more powerful than humanity as it exists today, but more powerful than humanity in the future. Future humans will have at their disposal the assistance of short-term AIs.

A salient possibility for me is that long-term-optimized AIs are only mildly more powerful (say, equivalent to a 50% compute increase), but that this is enough for almost everyone to use long-term AIs. If more of the world (ML community, leaders, regulators, general public) agrees that long-horizon-optimized AIs are more dangerous than short-horizon-optimized AIs, then short-horizon-optimized AIs can become the norm in spite of this. But it seems unclear to what extent this will happen, and so this similarly seems well worth pushing on, for a social impact-minded person/team.

I would love to discuss more in the future, but in the interest of time (and because this is already quite long), I'm starting with what I expect are the most fruitful lines.

Thank you! I think that what we see right now is that as the horizon grows, the more "tricks" we need to make end-to-end learning works, to the extent that it might not really be end to end. So while supervised learning is very successful, and seems to be quite robust to choice of architecture, loss functions, etc., in RL we need to be much more careful, and often things won't work "out of the box" in a purely end to end fashion.

 

I think the question would be how performance scales with horizon, if the returns are rapidly diminishing, and the cost to train is rapidly increasing (as might well be the case because of diminishing gradient signals, and much smaller availability of data),  then it could be that the "sweet spot" of what is economical to train would remain at a reasonably short horizon (far shorter than the planning needed to take over the world) for a long time. 

Claim 3: There may be fundamental “scaling laws” governing the amount of performance AI systems can achieve as a function of the data and computational resources.

I'm personally pretty sympathetic to the idea that there are indeed metrics through which model progress is continuous (both as a function of scale and over the course of training). 

That being said: smooth performance along one metric doesn't necessarily imply smooth downstream performance! (E.g. from your "SGD learns parity close to the computational limit" paper, even though there exist smooth progress measures on how small neural networks learn parity, this does not explain away the sharp increase in accuracy. See also the results from the modular addition task.)

In particular, it's empirically true that smooth progress of log loss does not necessarily imply smooth progress on downstream performance. For example, in both the BIG-Bench and Wei et al's "Emergent Abilities of Large Language Models" papers, we see that smooth performance on cross entropy loss or does not imply continuous smooth progress in terms of error rate. And though GPT-3 follows the same log loss scaling curve as GPT-2, I'm not sure anyone would have predicted the suite of new abilities that would arise alongside the decrease in log loss.

(It also doesn't rule out the existence of better scaffolding or prompting techniques like Chain-of-Thought, which can both significantly improve downstream performance and even change the shape of scaling curves, without additional training).

It is indeed the case that sometimes we see phase transitions / discontinuous improvements, and this is an area which I am very interested in. Note however that (while not in our paper) typically in graphs such as BIG-Bench, the X axis is something like log number of parameters. So it does seem you pay quite a price to achieve improvement. 

The claim there is not so much about the shape of the laws but rather about potential (though  as you say, not certain at all) limitations as to what improvements you can achieve through pure software alone, without investing more compute and/or data. Some other (very rough) calculations of costs are attempted in my previous blog post.

Yeah, I agree that a lot of the “phase transitions” look more discontinuous than they actually are due to the log on the x axis — the OG grokking paper definitely commits this sin, for example.

(I think there’s also another disagreement here about how close humans are to this natural limit.)