Near-term motivation for AGI alignment

AGI alignment work is usually considered “longtermist”, which is about preserving humanity’s long-term potential. This was the primary motivation for this work when the alignment field got started around 20 years ago, and AGI seemed far away or impossible to most people in AI. However, given the current rate of progress towards general AI capabilities, there is an increasingly relevant near-term motivation to think about alignment, even if you mostly or only care about people alive today. This is most of my personal motivation for working on alignment.

I would not be surprised if AGI is reached in the next few decades, similarly to the latest AI expert survey‘s median of 2059 for human-level AI (as estimated by authors at top ML conferences) and the Metaculus median of 2039. The Precipice gives a 10% probability of human extinction this century due to AI, i.e. within the lifetime of children alive today (and I would expect most of this probability to be concentrated in the next few decades, i.e. within our lifetimes). I used to refer to AGI alignment work as “long-term AI safety” but this term seems misleading now, since alignment would be more accurately described as “medium-term safety”. 

While AGI alignment has historically been associated with longtermism, there is a downside of referring to longtermist arguments for alignment concerns. Sometimes people seem to conclude that they don’t need to worry about alignment if they don’t care much about the long-term future. For example, one commonly cited argument for trying to reduce existential risk from AI is that “even if it’s unlikely and far away, it’s so important that we should worry about it anyway”. People understandably interpret this as Pascal’s mugging and bounce off. This kind of argument for alignment concerns is not very relevant these days, because existential risk from AI is not that unlikely (10% this century is actually a lot, and may be a conservative estimate) and AGI not that far away (an average of 36 years in the AI expert survey). 

Similarly, when considering specific paths to catastrophic risk from AGI, a typical longtermist scenario involves AGI inventing molecular nanotechnology, which understandably sounds implausible to most people. I think a more likely path to catastrophic risk would involve AGI precipitating other catastrophic risks like pandemics (e.g. by doing biotechnology research) or taking over the global economy. If you’d like to learn about the most pertinent arguments for alignment concerns and plausible paths for AI to gain an advantage over humanity, check out Holden Karnofsky’s Most Important Century blog post series. 

In terms of my own motivation, honestly I don’t care that much about whether humanity gets to colonize the stars, reducing astronomical waste, or large numbers of future people existing. These outcomes would be very cool but optional in my view. Of course I would like humanity to have a good long-term future, but I mostly care about people alive today. My main motivation for working on alignment is that I would like my loved ones and everyone else on the planet to have a future. 

Sometimes people worry about a tradeoff between alignment concerns and other aspects of AI safety, such as ethics / fairness, but I still think this tradeoff is pretty weak. There are also many common interests between alignment and ethics that would be great for these communities to coordinate on. This includes developing industry-wide safety standards and AI governance mechanisms, setting up model evaluations for safety, and slow and cautious deployment of advanced AI systems. Ultimately all these safety problems need to be solved to ensure that AGI systems have a positive impact on the world. I think the distribution of effort between AI capabilities and safety will need to shift more towards safety as more advanced AI systems are developed. 

In conclusion, you don’t have to be a longtermist to care about AGI alignment. I think the possible impacts on people alive today are significant enough to think about this problem, and the next decade is going to be a critical time for steering advanced AI technology towards safety. If you’d like to contribute, here is a list of research agendas in this space, and a good course to get up to speed on the fundamentals of AGI alignment.

Refining the Sharp Left Turn threat model

(Coauthored with others on the alignment team and cross-posted from the alignment forum: part 1, part 2)

A sharp left turn (SLT) is a possible rapid increase in AI system capabilities (such as planning and world modeling) that could result in alignment methods no longer working. This post aims to make the sharp left turn scenario more concrete. We will discuss our understanding of the claims made in this threat model, propose some mechanisms for how a sharp left turn could occur, how alignment techniques could manage a sharp left turn or fail to do so.

Image credit: Adobe

Claims of the threat model

What are the main claims of the “sharp left turn” threat model?

Claim 1. Capabilities will generalize far (i.e., to many domains)

There is an AI system that:

• Performs well: it can accomplish impressive feats, or achieve high scores on valuable metrics.
• Generalizes, i.e., performs well in new domains, which were not optimized for during training, with no domain-specific tuning.

Generalization is a key component of this threat model because we’re not going to directly train an AI system for the task of disempowering humanity, so for the system to be good at this task, the capabilities it develops during training need to be more broadly applicable. 

Some optional sub-claims can be made that increase the risk level of the threat model:

Claim 1a [Optional]: Capabilities (in different “domains”) will all generalize at the same time

Claim 1b [Optional]: Capabilities will generalize far in a discrete phase transition (rather than continuously) 

Claim 2. Alignment techniques that worked previously will fail during this transition

• Qualitatively different alignment techniques are needed. The ways the techniques work apply to earlier versions of the AI technology, but not to the new version because the new version gets its capability through something new, or jumps to a qualitatively higher capability level (even if through “scaling” the same mechanisms).

Claim 3: Humans can’t intervene to prevent or align this transition 

• Path 1: humans don’t notice because it’s too fast (or they aren’t paying attention)
• Path 2: humans notice but are unable to make alignment progress in time
• Some combination of these paths, as long as the end result is insufficiently correct alignment

Possible takeaways from the coronavirus pandemic for slow AI takeoff

(Cross-posted to LessWrong. Summarized in Alignment Newsletter #104. Thanks to Janos Kramar for helpful feedback on this post.)

As the covid-19 pandemic unfolds, we can draw lessons from it for managing future global risks, such as other pandemics, climate change, and risks from advanced AI. In this post, I will focus on possible implications for AI risk. For a broader treatment of this question, I recommend FLI’s covid-19 page that includes expert interviews on the implications of the pandemic for other types of risks. 

A key element in AI risk scenarios is the speed of takeoff – whether advanced AI is developed gradually or suddenly. Paul Christiano’s post on takeoff speeds defines slow takeoff in terms of the economic impact of AI as follows: “There will be a complete 4 year interval in which world output doubles, before the first 1 year interval in which world output doubles.” It argues that slow AI takeoff is more likely than fast takeoff, but is not necessarily easier to manage, since it poses different challenges, such as large-scale coordination. This post expands on this point by examining some parallels between the coronavirus pandemic and a slow takeoff scenario. The upsides of slow takeoff include the ability to learn from experience, act on warning signs, and reach a timely consensus that there is a serious problem. I would argue that the covid-19 pandemic had these properties, but most of the world’s institutions did not take advantage of them. This suggests that, unless our institutions improve, we should not expect the slow AI takeoff scenario to have a good default outcome. 

Retrospective on the specification gaming examples list

My post about the specification gaming list was recently nominated for the LessWrong 2018 Review (sort of like a test of time award), which prompted me to write a retrospective (cross-posted here). 

I’ve been pleasantly surprised by how much this resource has caught on in terms of people using it and referring to it (definitely more than I expected when I made it). There were 30 examples on the list when was posted in April 2018, and 20 new examples have been contributed through the form since then.  I think the list has several properties that contributed to wide adoption: it’s fun, standardized, up-to-date, comprehensive, and collaborative.

Some of the appeal is that it’s fun to read about AI cheating at tasks in unexpected ways (I’ve seen a lot of people post on Twitter about their favorite examples from the list). The standardized spreadsheet format seems easier to refer to as well. I think the crowdsourcing aspect is also helpful – this helps keep it current and comprehensive, and people can feel some ownership of the list since can personally contribute to it. My overall takeaway from this is that safety outreach tools are more likely to be impactful if they are fun and easy for people to engage with.

This list had a surprising amount of impact relative to how little work it took me to put it together and maintain it. The hard work of finding and summarizing the examples was done by the people putting together the lists that the master list draws on (Gwern, Lehman, Olsson, Irpan, and others), as well as the people who submit examples through the form. What I do is put them together in a common format and clarify and/or shorten some of the summaries. I also curate the examples to determine whether they fit the definition of specification gaming (as opposed to simply a surprising behavior or solution). Overall, I’ve probably spent around 10 hours so far on creating and maintaining the list, which is not very much. This makes me wonder if there is other low hanging fruit in the safety resources space that we haven’t picked yet. 

I have been using it both as an outreach and research tool. On the outreach side, the resource has been helpful for making the argument that safety problems are hard and need general solutions, by making it salient just in how many ways things could go wrong. When presented with an individual example of specification gaming, people often have a default reaction of “well, you can just close the loophole like this”. It’s easier to see that this approach does not scale when presented with 50 examples of gaming behaviors. Any given loophole can seem obvious in hindsight, but 50 loopholes are much less so. I’ve found this useful for communicating a sense of the difficulty and importance of Goodhart’s Law. 

On the research side, the examples have been helpful for trying to clarify the distinction between reward gaming and tampering problems. Reward gaming happens when the reward function is designed incorrectly (so the agent is gaming the design specification), while reward tampering happens when the reward function is implemented incorrectly or embedded in the environment (and so can be thought of as gaming the implementation specification). The boat race example is reward gaming, since the score function was defined incorrectly, while the Qbert agent finding a bug that makes the platforms blink and gives the agent millions of points is reward tampering. We don’t currently have any real examples of the agent gaining control of the reward channel (probably because the action spaces of present-day agents are too limited), which seems qualitatively different from the numerous examples of agents exploiting implementation bugs. 

I’m curious what people find the list useful for – as a safety outreach tool, a research tool or intuition pump, or something else? I’d also be interested in suggestions for improving the list (formatting, categorizing, etc). Thanks everyone who has contributed to the resource so far!

Classifying specification problems as variants of Goodhart’s Law

(Coauthored with Ramana Kumar and cross-posted from the Alignment Forum. Summarized in Alignment Newsletter #76.)

There are a few different classifications of safety problems, including the Specification, Robustness and Assurance (SRA) taxonomy and the Goodhart’s Law taxonomy. In SRA, the specification category is about defining the purpose of the system, i.e. specifying its incentives.  Since incentive problems can be seen as manifestations of Goodhart’s Law, we explore how the specification category of the SRA taxonomy maps to the Goodhart taxonomy. The mapping is an attempt to integrate different breakdowns of the safety problem space into a coherent whole. We hope that a consistent classification of current safety problems will help develop solutions that are effective for entire classes of problems, including future problems that have not yet been identified.

The SRA taxonomy defines three different types of specifications of the agent’s objective: ideal (a perfect description of the wishes of the human designer), design (the stated objective of the agent) and revealed (the objective recovered from the agent’s behavior). It then divides specification problems into design problems (e.g. side effects) that correspond to a difference between the ideal and design specifications, and emergent problems (e.g. tampering) that correspond to a difference between the design and revealed specifications.

In the Goodhart taxonomy, there is a variable U* representing the true objective, and a variable U representing the proxy for the objective (e.g. a reward function). The taxonomy identifies four types of Goodhart effects: regressional (maximizing U also selects for the difference between U and U*), extremal (maximizing U takes the agent outside the region where U and U* are correlated), causal (the agent intervenes to maximize U in a way that does not affect U*), and adversarial (the agent has a different goal W and exploits the proxy U to maximize W).

We think there is a correspondence between these taxonomies: design problems are regressional and extremal Goodhart effects, while emergent problems are causal Goodhart effects. The rest of this post will explain and refine this correspondence.

Discussion on the machine learning approach to AI safety

At this year’s EA Global London conference, Jan Leike and I ran a discussion session on the machine learning approach to AI safety. We explored some of the assumptions and considerations that come up as we reflect on different research agendas. Slides for the discussion can be found here.

The discussion focused on two topics. The first topic examined assumptions made by the ML safety approach as a whole, based on the blog post Conceptual issues in AI safety: the paradigmatic gap. The second topic zoomed into specification problems, which both of us work on, and compared our approaches to these problems.

Is there a tradeoff between immediate and longer-term AI safety efforts?

Something I often hear in the machine learning community and media articles is “Worries about superintelligence are a distraction from the *real* problem X that we are facing today with AI” (where X = algorithmic bias, technological unemployment, interpretability, data privacy, etc). This competitive attitude gives the impression that immediate and longer-term safety concerns are in conflict. But is there actually a tradeoff between them?

We can make this question more specific: what resources might these two types of efforts be competing for?

Portfolio approach to AI safety research

Long-term AI safety is an inherently speculative research area, aiming to ensure safety of advanced future systems despite uncertainty about their design or algorithms or objectives. It thus seems particularly important to have different research teams tackle the problems from different perspectives and under different assumptions. While some fraction of the research might not end up being useful, a portfolio approach makes it more likely that at least some of us will be right.

In this post, I look at some dimensions along which assumptions differ, and identify some underexplored reasonable assumptions that might be relevant for prioritizing safety research. (In the interest of making this breakdown as comprehensive and useful as possible, please let me know if I got something wrong or missed anything important.)

Clopen AI: Openness in different aspects of AI development

There has been a lot of discussion about the appropriate level of openness in AI research in the past year – the OpenAI announcement, the blog post Should AI Be Open?, a response to the latter, and Nick Bostrom’s thorough paper Strategic Implications of Openness in AI development.

There is disagreement on this question within the AI safety community as well as outside it. Many people are justifiably afraid of concentrating power to create AGI and determine its values in the hands of one company or organization. Many others are concerned about the information hazards of open-sourcing AGI and the resulting potential for misuse. In this post, I argue that some sort of compromise between openness and secrecy will be necessary, as both extremes of complete secrecy and complete openness seem really bad. The good news is that there isn’t a single axis of openness vs secrecy – we can make separate judgment calls for different aspects of AGI development, and develop a set of guidelines.

To contribute to AI safety, consider doing AI research

Among those concerned about risks from advanced AI, I’ve encountered people who would be interested in a career in AI research, but are worried that doing so would speed up AI capability relative to safety. I think it is a mistake for AI safety proponents to avoid going into the field for this reason (better reasons include being well-positioned to do AI safety work, e.g. at MIRI or FHI). This mistake contributed to me choosing statistics rather than computer science for my PhD, which I have some regrets about, though luckily there is enough overlap between the two fields that I can work on machine learning anyway.

I think the value of having more AI experts who are worried about AI safety is far higher than the downside of adding a few drops to the ocean of people trying to advance AI. Here are several reasons for this:

1. Concerned researchers can inform and influence their colleagues, especially if they are outspoken about their views.
2. Studying and working on AI brings understanding of the current challenges and breakthroughs in the field, which can usefully inform AI safety work (e.g. wireheading in reinforcement learning agents).
3. Opportunities to work on AI safety are beginning to spring up within academia and industry, e.g. through FLI grants. In the next few years, it will be possible to do an AI-safety-focused PhD or postdoc in computer science, which would hit two birds with one stone.