Orphan answers
Back to Improve answers.
These 171 canonical answers are not marked as a related or follow-up to any other canonical answer, so cannot be found through the read interface by normal browsing. Feel free to add them to some! See a full list of available canonical questions or browse by tags.
Each major organization has a different approach. The research agendas are detailed and complex (see also AI Watch). Getting more brains working on any of them (and more money to fund them) may pay off in a big way, but it’s very hard to be confident which (if any) of them will actually work.
The following is a massive oversimplification, each organization actually pursues many different avenues of research, read the 2020 AI Alignment Literature Review and Charity Comparison for much more detail. That being said:
- The Machine Intelligence Research Institute focuses on foundational mathematical research to understand reliable reasoning, which they think is necessary to provide anything like an assurance that a seed AI built will do good things if activated.
- The Center for Human-Compatible AI focuses on Cooperative Inverse Reinforcement Learning and Assistance Games, a new paradigm for AI where they try to optimize for doing the kinds of things humans want rather than for a pre-specified utility function
- Paul Christano's Alignment Research Center focuses is on prosaic alignment, particularly on creating tools that empower humans to understand and guide systems much smarter than ourselves. His methodology is explained on his blog.
- The Future of Humanity Institute does work on crucial considerations and other x-risks, as well as AI safety research and outreach.
- Anthropic is a new organization exploring natural language, human feedback, scaling laws, reinforcement learning, code generation, and interpretability.
- OpenAI is in a state of flux after major changes to their safety team.
- DeepMind’s safety team is working on various approaches designed to work with modern machine learning, and does some communication via the Alignment Newsletter.
- EleutherAI is a Machine Learning collective aiming to build large open source language models to allow more alignment research to take place.
- Ought is a research lab that develops mechanisms for delegating open-ended thinking to advanced machine learning systems.
There are many other projects around AI Safety, such as the Windfall clause, Rob Miles’s YouTube channel, AI Safety Support, etc.
A machine superintelligence, if programmed with the right motivations, could potentially solve all the problems that humans are trying to solve but haven’t had the ingenuity or processing speed to solve yet. A superintelligence might cure disabilities and diseases, achieve world peace, give humans vastly longer and healthier lives, eliminate food and energy shortages, boost scientific discovery and space exploration, and so on.
Furthermore, humanity faces several existential risks in the 21st century, including global nuclear war, bioweapons, superviruses, and more. A superintelligent machine would be more capable of solving those problems than humans are.
See also:
When one person tells a set of natural language instructions to another person, they are relying on much other information which is already stored in the other person's mind.
If you tell me "don't harm other people," I already have a conception of what harm means and doesn't mean, what people means and doesn't mean, and my own complex moral reasoning for figuring out the edge cases in instances wherein harming people is inevitable or harming someone is necessary for self-defense or the greater good.
All of those complex definitions and systems of decision making are already in our mind, so it's easy to take them for granted. An AI is a mind made from scratch, so programming a goal is not as simple as telling it a natural language command.
Avoid directly responding to the question in the answer, repeat the relevant part of the question instead. For example, if the question is "Can we do X", answer "We might be able to do X, if we can do Y", not "Yes, if we can manage Y". This way, the answer will also work for the questions "Why can't we do X" and "What would happen if we tried to do X".
Linking to external sites is strongly encouraged, one of the most valuable things Stampy can do is help people find other parts of the alignment information ecosystem.
Consider enclosing newly introduced terms, likely to be unfamiliar to many readers, in speech marks. If unsure, Google the term (in speech marks!) and see if it shows up anywhere other than LessWrong, the Alignment Forum, etc. Be judicious, as it's easy to use too many, but used carefully they can psychologically cushion newbies from a lot of unfamiliar terminology - in this context they're saying something like "we get that we're hitting you with a lot of new vocab, and you might not know what this term means yet".
When selecting related questions, there shouldn't be more than four unless there's a really good reason for that (some questions are asking for it, like the "Why can't we just..." question). It's also recommended to include at least one more "enticing" question to draw users in (relating to the more sensational, sci-fi, philosophical/ethical side of things) alongside more bland/neutral questions.
We’re facing the challenge of “Philosophy With A Deadline”.
Many of the problems surrounding superintelligence are the sorts of problems philosophers have been dealing with for centuries. To what degree is meaning inherent in language, versus something that requires external context? How do we translate between the logic of formal systems and normal ambiguous human speech? Can morality be reduced to a set of ironclad rules, and if not, how do we know what it is at all?
Existing answers to these questions are enlightening but nontechnical. The theories of Aristotle, Kant, Mill, Wittgenstein, Quine, and others can help people gain insight into these questions, but are far from formal. Just as a good textbook can help an American learn Chinese, but cannot be encoded into machine language to make a Chinese-speaking computer, so the philosophies that help humans are only a starting point for the project of computers that understand us and share our values.
The field of AI alignment combines formal logic, mathematics, computer science, cognitive science, and philosophy in order to advance that project.
This is the philosophy; the other half of Bostrom’s formulation is the deadline. Traditional philosophy has been going on almost three thousand years; machine goal alignment has until the advent of superintelligence, a nebulous event which may be anywhere from a decades to centuries away.
If the alignment problem doesn’t get adequately addressed by then, we are likely to see poorly aligned superintelligences that are unintentionally hostile to the human race, with some of the catastrophic outcomes mentioned above. This is why so many scientists and entrepreneurs are urging quick action on getting machine goal alignment research up to an adequate level.
If it turns out that superintelligence is centuries away and such research is premature, little will have been lost. But if our projections were too optimistic, and superintelligence is imminent, then doing such research now rather than later becomes vital.
If by “solve alignment” you mean build a sufficiently performance-competitive superintelligence which has the goal of Coherent Extrapolated Volition or something else which captures human values, then yes. It would be able to deploy technology near the limits of physics (e.g. atomically precise manufacturing) to solve most of the other problems which face us, and steer the future towards a highly positive path for perhaps many billions of years until the heat death of the universe (barring more esoteric x-risks like encounters with advanced hostile civilizations, false vacuum decay, or simulation shutdown).
However, if you only have alignment of a superintelligence to a single human you still have the risk of misuse, so this should be at most a short-term solution. For example, what if Google creates a superintelligent AI, and it listens to the CEO of Google, and it’s programmed to do everything exactly the way the CEO of Google would want? Even assuming that the CEO of Google has no hidden unconscious desires affecting the AI in unpredictable ways, this gives one person a lot of power.
Research at the Alignment Research Center is led by Paul Christiano, best known for introducing the “Iterated Distillation and Amplification” and “Humans Consulting HCH” approaches. He and his team are now “trying to figure out how to train ML systems to answer questions by straightforwardly ‘translating’ their beliefs into natural language rather than by reasoning about what a human wants to hear.”
Chris Olah (after work at DeepMind and OpenAI) recently launched Anthropic, an AI lab focussed on the safety of large models. While his previous work was concerned with “transparency” and “interpretability” of large neural networks, especially vision models, Anthropic is focussing more on large language models, among other things working towards a "general-purpose, text-based assistant that is aligned with human values, meaning that it is helpful, honest, and harmless".
Stuart Russell and his team at the Center for Human-Compatible Artificial Intelligence (CHAI) have been working on inverse reinforcement learning (where the AI infers human values from observing human behavior) and corrigibility, as well as attempts to disaggregate neural networks into “meaningful” subcomponents (see Filan, et al.’s “Clusterability in neural networks” and Hod et al.'s “Detecting modularity in deep neural networks”).
Alongside the more abstract “agent foundations” work they have become known for, MIRI recently announced their “Visible Thoughts Project” to test the hypothesis that “Language models can be made more understandable (and perhaps also more capable, though this is not the goal) by training them to produce visible thoughts.”
OpenAI have recently been doing work on iteratively summarizing books (summarizing, and then summarizing the summary, etc.) as a method for scaling human oversight.
Stuart Armstrong’s recently launched AlignedAI are mainly working on concept extrapolation from familiar to novel contexts, something he believes is “necessary and almost sufficient” for AI alignment.
Redwood Research (Buck Shlegeris, et al.) are trying to “handicap' GPT-3 to only produce non-violent completions of text prompts. “The idea is that there are many reasons we might ultimately want to apply some oversight function to an AI model, like ‘don't be deceitful’, and if we want to get AI teams to apply this we need to be able to incorporate these oversight predicates into the original model in an efficient manner.”
Ought is an independent AI safety research organization led by Andreas Stuhlmüller and Jungwon Byun. They are researching methods for breaking up complex, hard-to-verify tasks into simpler, easier-to-verify tasks, with the aim of allowing us to maintain effective oversight over AIs.
One possible way to ensure the safety of a powerful AI system is to keep it contained in a software environment. There is nothing intrinsically wrong with this procedure - keeping an AI system in a secure software environment would make it safer than letting it roam free. However, even AI systems inside software environments might not be safe enough.
Humans sometimes put dangerous humans inside boxes to limit their ability to influence the external world. Sometimes, these humans escape their boxes. The security of a prison depends on certain assumptions, which can be violated. Yoshie Shiratori reportedly escaped prison by weakening the door-frame with miso soup and dislocating his shoulders.
Human written software has a high defect rate; we should expect a perfectly secure system to be difficult to create. If humans construct a software system they think is secure, it is possible that the security relies on a false assumption. A powerful AI system could potentially learn how its hardware works and manipulate bits to send radio signals. It could fake a malfunction and attempt social engineering when the engineers look at its code. As the saying goes: in order for someone to do something we had imagined was impossible requires only that they have a better imagination.
Experimentally, humans have convinced other humans to let them out of the box. Spooky.
Creating a high-quality single point of access where people can be onboarded and find resources around the alignment ecosystem seems likely high-impact.
Additionally, contributing to Stampy means being part of a community of co-learners who provide mentorship and encouragement to join the effort to give humanity a bight future.The near term and long term aspects of AI safety are both very important to work on. Research into superintelligence is an important part of the open letter, but the actual concern is very different from the Terminator-like scenarios that most media outlets round off this issue to. A much more likely scenario is a superintelligent system with neutral or benevolent goals that is misspecified in a dangerous way. Robust design of superintelligent systems is a complex interdisciplinary research challenge that will likely take decades, so it is very important to begin the research now, and a large part of the purpose of our research program is to make that happen. That said, the alarmist media framing of the issues is hardly useful for making progress in either the near term or long term domain.
While it is true that a computer program always will do exactly what it is programmed to do, a big issue is that it is difficult to ensure that this is the same as what you intended it to do. Even small computer programs have bugs or glitches, and when programs become as complicated as AGIs will be, it becomes exceedingly difficult to anticipate how the program will behave when ran. This is the problem of AI alignment in a nutshell.
Nick Boström created the famous paperclip maximizer thought experiment to illustrate this point. Imagine you are an industrialist who owns a paperclip factory, and imagine you've just received a superintelligent AGI to work for you. You instruct the AGI to "produce as many paperclips as possible". If you've given the AGI no further instructions, the AGI will immediately acquire several instrumental goals.
- It will want to prevent you from turning itself off (If you turn off the AI, this will reduce the amount of paperclips it can produce)
- It will want to acquire as much power and resources for itself as possible (because the more resources it has access to, the more paperclips it can produce)
- It will eventually want to turn the entire universe into a paperclips including you and all other humans, as this is the state of the world that maximizes the amount of paper clips produced.
These consequences might be seen as undesirable by the industrialist, as the only reason the industrialist wanted paperclips in the first place, presumably was so he/she could sell them and make money. However, the AGI only did exactly what it was told to. The issue was that what the AGI was instructed to do, lead to it doing things the industrialist did not anticipate (and did not want).
Some good videos that explore this issue more in depth:
The basic concern as AI systems become increasingly powerful is that they won’t do what we want them to do – perhaps because they aren’t correctly designed, perhaps because they are deliberately subverted, or perhaps because they do what we tell them to do rather than what we really want them to do (like in the classic stories of genies and wishes.) Many AI systems are programmed to have goals and to attain them as effectively as possible – for example, a trading algorithm has the goal of maximizing profit. Unless carefully designed to act in ways consistent with human values, a highly sophisticated AI trading system might exploit means that even the most ruthless financier would disavow. These are systems that literally have a mind of their own, and maintaining alignment between human interests and their choices and actions will be crucial.
Canonical answers may be served to readers by Stampy, so only answers which have a reasonably high stamp score should be marked as canonical. All canonical answers are open to be collaboratively edited and updated, and they should represent a consensus response (written from the Stampy Point Of View) to a question which is within Stampy's scope.
Answers to questions from YouTube comments should not be marked as canonical, and will generally remain as they were when originally written since they have details which are specific to an idiosyncratic question. YouTube answers may be forked into wiki answers, in order to better respond to a particular question, in which case the YouTube question should have its canonical version field set to the new more widely useful question.
The AGI Safety Fundamentals Course is a arguably the best way to get up to speed on alignment, you can sign up to go through it with many other people studying and mentorship or read their materials independently.
Other great ways to explore include:
- AXRP is a podcast with high quality interviews with top alignment researchers.
- The AI Safety Papers database is a search and browsing interface for most of the transformative AI literature.
- Reading posts on the Alignment Forum can be valuable (see their curated posts and tags).
- Taking a deep dive into Yudkowsky's models of the challenges to aligned AI, via the Arbital Alignment pages.
- Signing up to the Alignment Newsletter for an overview of current developments, and reading through some of the archives (or listening to the podcast).
- Reading some of the introductory books.
- More on AI Safety Support's list of links, Nonlinear's list of technical courses, reading lists, and curriculums, Stampy's canonical answers list, and Vika's resources list.
You might also want to consider reading Rationality: A-Z which covers a lot of skills that are valuable to acquire for people trying to think about large and complex issues, with The Rationalist's Guide to the Galaxy available as a shorter and more accessible AI-focused option.
Imagine, for example, that you are tasked with reducing traffic congestion in San Francisco at all costs, i.e. you do not take into account any other constraints. How would you do it? You might start by just timing traffic lights better. But wouldn’t there be less traffic if all the bridges closed down from 5 to 10AM, preventing all those cars from entering the city? Such a measure obviously violates common sense, and subverts the purpose of improving traffic, which is to help people get around – but it is consistent with the goal of “reducing traffic congestion”.
We could shut down weaker systems, and this would be a useful guardrail against certain types of problem caused by narrow AI. However, once an AGI establishes itself, we could not unless it was corrigible and willing to let humans adjust it. There may be a period in the early stages of an AGI's development where it would be trying very hard to convince us that we should not shut it down and/or hiding itself and/or recursively self-improving and/or making copies of itself onto every server on earth.
Instrumental Convergence and the Stop Button Problem are the key reasons it would not be simple to shut down a non corrigible advanced system. If the AI wants to collect stamps, being turned off means it gets less stamps, so even without an explicit goal of not being turned off it has an instrumental reason to avoid being turned off (e.g. once it acquires a detailed world model and general intelligence, it is likely to realise that by playing nice and pretending to be aligned if you have the power to turn it off, establishing control over any system we put in place to shut it down, and eliminating us if it has the power to reliably do so and we would otherwise pose a threat).
The Rob Miles AI Discord is the hub of all things Stampy. If you want to be part of the project and don't have access yet, ask plex#1874 on Discord (or plex on wiki).
You can also talk to us on the public Discord! Try #suggestions or #general, depending on what you want to talk about.
Blindly following the trendlines while forecasting technological progress is certainly a risk (affectionately known in AI circles as “pulling a Kurzweill”), but sometimes taking an exponential trend seriously is the right response.
Consider economic doubling times. In 1 AD, the world GDP was about $20 billion; it took a thousand years, until 1000 AD, for that to double to $40 billion. But it only took five hundred more years, until 1500, or so, for the economy to double again. And then it only took another three hundred years or so, until 1800, for the economy to double a third time. Someone in 1800 might calculate the trend line and say this was ridiculous, that it implied the economy would be doubling every ten years or so in the beginning of the 21st century. But in fact, this is how long the economy takes to double these days. To a medieval, used to a thousand-year doubling time (which was based mostly on population growth!), an economy that doubled every ten years might seem inconceivable. To us, it seems normal.
Likewise, in 1965 Gordon Moore noted that semiconductor complexity seemed to double every eighteen months. During his own day, there were about five hundred transistors on a chip; he predicted that would soon double to a thousand, and a few years later to two thousand. Almost as soon as Moore’s Law become well-known, people started saying it was absurd to follow it off a cliff – such a law would imply a million transistors per chip in 1990, a hundred million in 2000, ten billion transistors on every chip by 2015! More transistors on a single chip than existed on all the computers in the world! Transistors the size of molecules! But of course all of these things happened; the ridiculous exponential trend proved more accurate than the naysayers.
None of this is to say that exponential trends are always right, just that they are sometimes right even when it seems they can’t possibly be. We can’t be sure that a computer using its own intelligence to discover new ways to increase its intelligence will enter a positive feedback loop and achieve superintelligence in seemingly impossibly short time scales. It’s just one more possibility, a worry to place alongside all the other worrying reasons to expect a moderate or hard takeoff.
- The Orthogonality Thesis: AI could have almost any goal while at the same time having high intelligence (aka ability to succeed at those goals). This means that we could build a very powerful agent which would not necessarily share human-friendly values. For example, the classic paperclip maximizer thought experiment explores this with an AI which has a goal of creating as many paperclips as possible, something that humans are (mostly) indifferent to, and as a side effect ends up destroying humanity to make room for more paperclip factories.
- Complexity of value: What humans care about is not simple, and the space of all goals is large, so virtually all goals we could program into an AI would lead to worlds not valuable to humans if pursued by a sufficiently powerful agent. If we, for example, did not include our value of diversity of experience, we could end up with a world of endlessly looping simple pleasures, rather than beings living rich lives.
- Instrumental Convergence: For almost any goal an AI has there are shared ‘instrumental’ steps, such as acquiring resources, preserving itself, and preserving the contents of its goals. This means that a powerful AI with goals that were not explicitly human-friendly would predictably both take actions that lead to the end of humanity (e.g. using resources humans need to live to further its goals, such as replacing our crop fields with vast numbers of solar panels to power its growth, or using the carbon in our bodies to build things) and prevent us from turning it off or altering its goals.
An AGI which has recursively self-improved into a superintelligence would be capable of either resisting our attempts to modify incorrectly specified goals, or realizing it was still weaker than us and acting deceptively aligned until it was highly sure it could win in a confrontation. AGI would likely prevent a human from shutting it down unless the AGI was designed to be corrigible. See Why can't we just turn the AI off if it starts to misbehave for more information.
As with most things, the best way to form your views on AI safety is to read up on the various ideas and opinions that knowledgeable people in the field have, and to compare them and form your own perspective. There are several good places to start. One of them is the Machine Intelligence Research Institute`s "Why AI safety?" info page. The article contains links to relevant research. The Effective Altruism Forum has an article called "How I formed my own views on AI safety", which could also be pretty helpful. Here is a Robert Miles youtube video that can be a good place to start as well. Otherwise, there are various articles about it, like this one, from Vox.
As is often said, it's difficult to make predictions, especially about the future. This has not stopped many people thinking about when AI will transform the world, but all predictions should come with a warning that it's a hard domain to find anything like certainty.
This report for the Open Philanthropy Project is perhaps the most careful attempt so far (and generates these graphs, which peak at 2042), and there's been much discussion including this reply and analysis which argues that we likely need less compute than the OpenPhil report expects.
There have also been expert surveys, and many people have shared various thoughts. Berkeley AI professor Stuart Russell has given his best guess as “sometime in our children’s lifetimes”, and Ray Kurzweil (Futurist and Google’s director of engineering) predicts human level AI by 2029 and the singularity by 2045. The Metaculus question on publicly known AGI has a median of around 2029 (around 10 years sooner than it was before the GPT-3 AI showed unexpected ability on a broad range of tasks).
The consensus answer, if there was one, might be something like: “highly uncertain, maybe not for over a hundred years, maybe in less than 15, with around the middle of the century looking fairly plausible”.
All the content below is in English:
- The AI technical safety section of the 80,000 Hours Podcast;
- The AI X-risk Research Podcast, hosted by Daniel Filan;
- The AI Alignment Podcast hosted by Lucas Perry from the Future of Life Institute (ran ~monthly from April 2018 to March 2021);
- The Alignment Newsletter Podcast by Rob Miles (an audio version of the weekly newsletter).
Sort answer: No, and could be dangerous to try.
Slightly longer answer: With any realistic real-world task assigned to an AGI, there are so many ways in which it could go wrong that trying to block them all off by hand is a hopeless task, especially when something smarter than you is trying to find creative new things to do. You run into the nearest unblocked strategy problem.
It may be dangerous to try this because if you try and hard-code a large number of things to avoid it increases the chance that there’s a bug in your code which causes major problems, simply by increasing the size of your codebase.
