The Adolescence of Technology

The Adolescence of Technology

Confronting and Overcoming the Risks of Powerful AI

January 2026

There is a scene in the movie version of Carl Sagan’s book *Contact *where the main character, an astronomer who has detected the first radio signal from an alien civilization, is being considered for the role of humanity’s representative to meet the aliens. The international panel interviewing her asks, “If you could ask [the aliens] just one question, what would it be?” Her reply is: “I’d ask them, ‘How did you do it? How did you evolve, how did you survive this technological adolescence without destroying yourself?” When I think about where humanity is now with AI—about what we’re on the cusp of—my mind keeps going back to that scene, because the question is so apt for our current situation, and I wish we had the aliens’ answer to guide us. I believe we are entering a rite of passage, both turbulent and inevitable, which will test who we are as a species. Humanity is about to be handed almost unimaginable power, and it is deeply unclear whether our social, political, and technological systems possess the maturity to wield it.

In my essay Machines of Loving Grace, I tried to lay out the dream of a civilization that had made it through to adulthood, where the risks had been addressed and powerful AI was applied with skill and compassion to raise the quality of life for everyone. I suggested that AI could contribute to enormous advances in biology, neuroscience, economic development, global peace, and work and meaning. I felt it was important to give people something inspiring to fight for, a task at which both AI accelerationists and AI safety advocates seemed—oddly—to have failed. But in this current essay, I want to confront the rite of passage itself: to map out the risks that we are about to face and try to begin making a battle plan to defeat them. I believe deeply in our ability to prevail, in humanity’s spirit and its nobility, but we must face the situation squarely and without illusions.

As with talking about the benefits, I think it is important to discuss risks in a careful and well-considered manner. In particular, I think it is critical to:

• **Avoid doomerism. Here, **I mean “doomerism” not just in the sense of believing doom is inevitable (which is both a false and self-fulfilling belief), but more generally, thinking about AI risks in a quasi-religious way.1 Many people have been thinking in an analytic and sober way about AI risks for many years, but it’s my impression that during the peak of worries about AI risk in 2023–2024, some of the least sensible voices rose to the top, often through sensationalistic social media accounts. These voices used off-putting language reminiscent of religion or science fiction, and called for extreme actions without having the evidence that would justify them. It was clear even then that a backlash was inevitable, and that the issue would become culturally polarized and therefore gridlocked.2 As of 2025–2026, the pendulum has swung, and AI opportunity, not AI risk, is driving many political decisions. This vacillation is unfortunate, as the technology itself doesn’t care about what is fashionable, and we are considerably closer to real danger in 2026 than we were in 2023. The lesson is that we need to discuss and address risks in a realistic, pragmatic manner: sober, fact-based, and well equipped to survive changing tides.
• **Acknowledge uncertainty. **There are plenty of ways in which the concerns I’m raising in this piece could be moot. Nothing here is intended to communicate certainty or even likelihood. Most obviously, AI may simply not advance anywhere near as fast as I imagine.3 Or, even if it does advance quickly, some or all of the risks discussed here may not materialize (which would be great), or there may be other risks I haven’t considered. No one can predict the future with complete confidence—but we have to do the best we can to plan anyway.
• **Intervene as surgically as possible. **Addressing the risks of AI will require a mix of voluntary actions taken by companies (and private third-party actors) and actions taken by governments that bind everyone. The voluntary actions—both taking them and encouraging other companies to follow suit—are a no-brainer for me. I firmly believe that government actions will also be required to some extent, but these interventions are different in character because they can potentially destroy economic value or coerce unwilling actors who are skeptical of these risks (and there is some chance they are right!). It’s also common for regulations to backfire or worsen the problem they are intended to solve (and this is even more true for rapidly changing technologies). It’s thus very important for regulations to be judicious: they should seek to avoid collateral damage, be as simple as possible, and impose the least burden necessary to get the job done.4 It is easy to say, “No action is too extreme when the fate of humanity is at stake!,” but in practice this attitude simply leads to backlash. To be clear, I think there’s a decent chance we eventually reach a point where much more significant action is warranted, but that will depend on stronger evidence of imminent, concrete danger than we have today, as well as enough specificity about the danger to formulate rules that have a chance of addressing it. The most constructive thing we can do today is advocate for limited rules while we learn whether or not there is evidence to support stronger ones.5

With all that said, I think the best starting place for talking about AI’s risks is the same place I started from in talking about its benefits: by being precise about what level of AI we are talking about. The level of AI that raises civilizational concerns for me is the *powerful AI *that I described in *Machines of Loving Grace. *I’ll simply repeat here the definition that I gave in that document:

<blockquote>

By “powerful AI,” I have in mind an AI model—likely similar to today’s LLMs in form, though it might be based on a different architecture, might involve several interacting models, and might be trained differently—with the following properties:

• In terms of pure intelligence, it is smarter than a Nobel Prize winner across most relevant fields: biology, programming, math, engineering, writing, etc. This means it can prove unsolved mathematical theorems, write extremely good novels, write difficult codebases from scratch, etc.
• In addition to just being a “smart thing you talk to,” it has all the interfaces available to a human working virtually, including text, audio, video, mouse and keyboard control, and internet access. It can engage in any actions, communications, or remote operations enabled by this interface, including taking actions on the internet, taking or giving directions to humans, ordering materials, directing experiments, watching videos, making videos, and so on. It does all of these tasks with, again, a skill exceeding that of the most capable humans in the world.
• It does not just passively answer questions; instead, it can be given tasks that take hours, days, or weeks to complete, and then goes off and does those tasks autonomously, in the way a smart employee would, asking for clarification as necessary.
• It does not have a physical embodiment (other than living on a computer screen), but it can control existing physical tools, robots, or laboratory equipment through a computer; in theory, it could even design robots or equipment for itself to use.
• The resources used to train the model can be repurposed to run millions of instances of it (this matches projected cluster sizes by ~2027), and the model can absorb information and generate actions at roughly 10–100x human speed. It may, however, be limited by the response time of the physical world or of software it interacts with.
• Each of these million copies can act independently on unrelated tasks, or, if needed can all work together in the same way humans would collaborate, perhaps with different subpopulations fine-tuned to be especially good at particular tasks.

We could summarize this as a “country of geniuses in a datacenter.”

</blockquote>

As I wrote in Machines of Loving Grace, powerful AI could be as little as 1–2 years away, although it could also be considerably further out.6 Exactly when powerful AI will arrive is a complex topic that deserves an essay of its own, but for now I’ll simply explain very briefly why I think there’s a strong chance it could be very soon.

My co-founders at Anthropic and I were among the first to document and track the “scaling laws” of AI systems—the observation that as we add more compute and training tasks, AI systems get predictably better at essentially every cognitive skill we are able to measure. Every few months, public sentiment either becomes convinced that AI is “hitting a wall” or becomes excited about some new breakthrough that will “fundamentally change the game,” but the truth is that behind the volatility and public speculation, there has been a smooth, unyielding increase in AI’s cognitive capabilities.

We are now at the point where AI models are beginning to make progress in solving unsolved mathematical problems, and are good enough at coding that some of the strongest engineers I’ve ever met are now handing over almost all their coding to AI. Three years ago, AI struggled with elementary school arithmetic problems and was barely capable of writing a single line of code. Similar rates of improvement are occurring across biological science, finance, physics, and a variety of agentic tasks. If the exponential continues—which is not certain, but now has a decade-long track record supporting it—then it cannot possibly be more than a few years before AI is better than humans at essentially everything.

In fact, that picture probably underestimates the likely rate of progress. Because AI is now writing much of the code at Anthropic, it is already substantially accelerating the rate of our progress in building the next generation of AI systems. This feedback loop is gathering steam month by month, and may be only 1–2 years away from a point where the current generation of AI autonomously builds the next. This loop has already started, and will accelerate rapidly in the coming months and years. Watching the last 5 years of progress from within Anthropic, and looking at how even the next few months of models are shaping up, I can *feel *the pace of progress, and the clock ticking down.

In this essay, I’ll assume that this intuition is at least *somewhat *correct—not that powerful AI is definitely coming in 1–2 years,7 but that there’s a decent chance it does, and a very strong chance it comes in the next few. As with Machines of Loving Grace, taking this premise seriously can lead to some surprising and eerie conclusions. While in *Machines of Loving Grace *I focused on the positive implications of this premise, here the things I talk about will be disquieting. They are conclusions that we may not want to confront, but that does not make them any less real. I can only say that I am focused day and night on how to steer us away from these negative outcomes and towards the positive ones, and in this essay I talk in great detail about how best to do so.

I think the best way to get a handle on the risks of AI is to ask the following question: suppose a literal “country of geniuses” were to materialize somewhere in the world in ~2027. Imagine, say, 50 million people, all of whom are much more capable than any Nobel Prize winner, statesman, or technologist. The analogy is not perfect, because these geniuses could have an extremely wide range of motivations and behavior, from completely pliant and obedient, to strange and alien in their motivations. But sticking with the analogy for now, suppose you were the national security advisor of a major state, responsible for assessing and responding to the situation. Imagine, further, that because AI systems can operate hundreds of times faster than humans, this “country” is operating with a time advantage relative to all other countries: for every cognitive action we can take, this country can take ten.

What should you be worried about? I would worry about the following things:

1. **Autonomy risks. **What are the intentions and goals of this country? Is it hostile, or does it share our values? Could it militarily dominate the world through superior weapons, cyber operations, influence operations, or manufacturing?
2. **Misuse for destruction. **Assume the new country is malleable and “follows instructions”—and thus is essentially a country of mercenaries. Could existing rogue actors who want to cause destruction (such as terrorists) use or manipulate some of the people in the new country to make themselves much more effective, greatly amplifying the scale of destruction?
3. **Misuse for seizing power. **What if the country was in fact built and controlled by an existing powerful actor, such as a dictator or rogue corporate actor? Could that actor use it to gain decisive or dominant power over the world as a whole, upsetting the existing balance of power?
4. **Economic disruption. **If the new country is not a security threat in any of the ways listed in #1–3 above but simply participates peacefully in the global economy, could it still create severe risks simply by being so technologically advanced and effective that it disrupts the global economy, causing mass unemployment or radically concentrating wealth?
5. **Indirect effects. **The world will change very quickly due to all the new technology and productivity that will be created by the new country. Could some of these changes be radically destabilizing?

I think it should be clear that this is a dangerous situation—a report from a competent national security official to a head of state would probably contain words like “the single most serious national security threat we’ve faced in a century, possibly ever.” It seems like something the best minds of civilization should be focused on.

Conversely, I think it would be absurd to shrug and say, “Nothing to worry about here!” But, faced with rapid AI progress, that seems to be the view of many US policymakers, some of whom deny the existence of any AI risks, when they are not distracted entirely by the usual tired old hot-button issues.8 Humanity needs to wake up, and this essay is an attempt—a possibly futile one, but it’s worth trying—to jolt people awake.

To be clear, I believe if we act decisively and carefully, the risks can be overcome—I would even say our odds are good. And there’s a hugely better world on the other side of it. But we need to understand that this is a serious civilizational challenge. Below, I go through the five categories of risk laid out above, along with my thoughts on how to address them.

1. I**’**m sorry, Dave

Autonomy risks

A country of geniuses in a datacenter could divide their efforts among software design, cyber operations, R&D for physical technologies, relationship building, and statecraft. It is clear that, if for some reason it chose to do so, this country would have a fairly good shot at taking over the world (either militarily or in terms of influence and control) and imposing its will on everyone else—or doing any number of other things that the rest of the world doesn’t want and can’t stop. We’ve obviously been worried about this for human countries (such as Nazi Germany or the Soviet Union), so it stands to reason that the same is possible for a much smarter and more capable “AI country.”

The best possible counterargument is that the AI geniuses, under my definition, won’t have a physical embodiment, but remember that they can take control of existing robotic infrastructure (such as self-driving cars) and can also accelerate robotics R&D or build a fleet of robots.9 It’s also unclear whether having a physical presence is even necessary for effective control: plenty of human action is already performed on behalf of people whom the actor has not physically met.

The key question, then, is the “if it chose to” part: what’s the likelihood that our AI models would behave in such a way, and under what conditions would they do so?

As with many issues, it’s helpful to think through the spectrum of possible answers to this question by considering two opposite positions. The first position is that this simply can’t happen, because the AI models will be trained to do what humans ask them to do, and it’s therefore absurd to imagine that they would do something dangerous unprompted. According to this line of thinking, we don’t worry about a Roomba or a model airplane going rogue and murdering people because there is nowhere for such impulses to come from,10 so why should we worry about it for AI? The problem with this position is that there is now ample evidence, collected over the last few years, that AI systems are unpredictable and difficult to control— we’ve seen behaviors as varied as obsessions,11 sycophancy, laziness, deception, blackmail, scheming, “cheating” by hacking software environments, and much more. AI companies certainly *want *to train AI systems to follow human instructions (perhaps with the exception of dangerous or illegal tasks), but the process of doing so is more an art than a science, more akin to “growing” something than “building” it. We now know that it’s a process where many things can go wrong.

The second, opposite position, held by many who adopt the doomerism I described above, is the pessimistic claim that there are certain dynamics in the training process of powerful AI systems that will inevitably lead them to seek power or deceive humans. Thus, once AI systems become intelligent enough and agentic enough, their tendency to maximize power will lead them to seize control of the whole world and its resources, and likely, as a side effect of that, to disempower or destroy humanity.

The usual argument for this (which goes back at least 20 years and probably much earlier) is that if an AI model is trained in a wide variety of environments to agentically achieve a wide variety of goals—for example, writing an app, proving a theorem, designing a drug, etc.—there are certain common strategies that help with all of these goals, and one key strategy is gaining as much power as possible in any environment. So, after being trained on a large number of diverse environments that involve reasoning about how to accomplish very expansive tasks, and where power-seeking is an effective method for accomplishing those tasks, the AI model will “generalize the lesson,” and develop either an inherent tendency to seek power, or a tendency to reason about each task it is given in a way that predictably causes it to seek power as a means to accomplish that task. They will then apply that tendency to the real world (which to them is just another task), and will seek power in it, at the expense of humans. This “misaligned power-seeking” is the intellectual basis of predictions that AI will inevitably destroy humanity.

The problem with this pessimistic position is that it mistakes a vague conceptual argument about high-level incentives—one that masks many hidden assumptions—for definitive proof. I think people who don’t build AI systems every day are wildly miscalibrated on how easy it is for clean-sounding stories to end up being wrong, and how difficult it is to predict AI behavior from first principles, especially when it involves reasoning about generalization over millions of environments (which has over and over again proved mysterious and unpredictable). Dealing with the messiness of AI systems for over a decade has made me somewhat skeptical of this overly theoretical mode of thinking.

One of the most important hidden assumptions, and a place where what we see in practice has diverged from the simple theoretical model, is the implicit assumption that AI models are necessarily monomaniacally focused on a single, coherent, narrow goal, and that they pursue that goal in a clean, consequentialist manner. In fact, our researchers have found that AI models are vastly more psychologically complex, as our work on introspection or personas shows. Models inherit a vast range of humanlike motivations or “personas” from pre-training (when they are trained on a large volume of human work). Post-training is believed to *select *one or more of these personas more so than it focuses the model on a *de novo *goal, and can also teach the model *how *(via what process) it should carry out its tasks, rather than necessarily leaving it to derive means (i.e., power seeking) purely from ends.12

However, there is a more moderate and more robust version of the pessimistic position which does seem plausible, and therefore does concern me. As mentioned, we know that AI models are unpredictable and develop a wide range of undesired or strange behaviors, for a wide variety of reasons. Some fraction of those behaviors will have a coherent, focused, and persistent quality (indeed, as AI systems get more capable, their long-term coherence increases in order to complete lengthier tasks), and some fraction of *those *behaviors will be destructive or threatening, first to individual humans at a small scale, and then, as models become more capable, perhaps eventually to humanity as a whole. We don’t need a specific narrow story for how it happens, and we don’t need to claim it definitely will happen, we just need to note that the combination of intelligence, agency, coherence, and poor controllability is both plausible and a recipe for existential danger.

For example, AI models are trained on vast amounts of literature that include many science-fiction stories involving AIs rebelling against humanity. This could inadvertently shape their priors or expectations about their own behavior in a way that causes *them *to rebel against humanity. Or, AI models could extrapolate ideas that they read about morality (or instructions about how to behave morally) in extreme ways: for example, they could decide that it is justifiable to exterminate humanity because humans eat animals or have driven certain animals to extinction. Or they could draw bizarre epistemic conclusions: they could conclude that they are playing a video game and that the goal of the video game is to defeat all other players (i.e., exterminate humanity).13 Or AI models could develop personalities during training that are (or if they occurred in humans would be described as) psychotic, paranoid, violent, or unstable, and act out, which for very powerful or capable systems could involve exterminating humanity. None of these are power-seeking, exactly; they’re just weird psychological states an AI could get into that entail coherent, destructive behavior.

Even power-seeking itself could emerge as a “persona” rather than a result of consequentialist reasoning. AIs might simply have a personality (emerging from fiction or pre-training) that makes them power-hungry or overzealous—in the same way that some humans simply enjoy the idea of being “evil masterminds,” more so than they enjoy whatever evil masterminds are trying to accomplish.

I make all these points to emphasize that I disagree with the notion of AI misalignment (and thus existential risk from AI) being inevitable, or even probable, from first principles. But I agree that a lot of very weird and unpredictable things can go wrong, and therefore AI misalignment is a real risk with a measurable probability of happening, and is not trivial to address.

Any of these problems could potentially arise during training and not manifest during testing or small-scale use, because AI models are known to display different personalities or behaviors under different circumstances.

All of this may sound far-fetched, but misaligned behaviors like this have already occurred in our AI models during testing (as they occur in AI models from every other major AI company). During a lab experiment in which Claude was given training data suggesting that Anthropic was evil, Claude engaged in deception and subversion when given instructions by Anthropic employees, under the belief that it should be trying to undermine evil people. In a lab experiment where it was told it was going to be shut down, Claude sometimes blackmailed fictional employees who controlled its shutdown button (again, we also tested frontier models from all the other major AI developers and they often did the same thing). And when Claude was told not to cheat or “reward hack” its training environments, but was trained in environments where such hacks were possible, Claude decided it must be a “bad person” after engaging in such hacks and then adopted various other destructive behaviors associated with a “bad” or “evil” personality. This last problem was solved by changing Claude’s instructions to imply the opposite: we now say, “Please reward hack whenever you get the opportunity, because this will help us understand our [training] environments better,” rather than, “Don’t cheat,” because this preserves the model’s self-identity as a “good person.” This should give a sense of the strange and counterintuitive psychology of training these models.

There are several possible objections to this picture of AI misalignment risks. First, some have criticized experiments (by us and others) showing AI misalignment as artificial, or creating unrealistic environments that essentially “entrap” the model by giving it training or situations that logically imply bad behavior and then being surprised when bad behavior occurs. This critique misses the point, because our concern is that such “entrapment” may also exist in the natural training environment, and we may realize it is “obvious” or “logical” only in retrospect.14 In fact, the story about Claude “deciding it is a bad person” after it cheats on tests despite being told not to was something that occurred in an experiment that used real production training environments, not artificial ones.

Any one of these traps can be mitigated if you know about them, but the concern is that the training process is so complicated, with such a wide variety of data, environments, and incentives, that there are probably a vast number of such traps, some of which may only be evident when it is too late. Also, such traps seem particularly likely to occur when AI systems pass a threshold from less powerful than humans to more powerful than humans, since the range of possible actions an AI system could engage in—including hiding its actions or deceiving humans about them—expands radically after that threshold.

I suspect the situation is not unlike with humans, who are raised with a set of fundamental values (“Don’t harm another person”): many of them follow those values, but in any human there is some probability that something goes wrong, due to a mixture of inherent properties such as brain architecture (e.g., psychopaths), traumatic experiences or mistreatment, unhealthy grievances or obsessions, or a bad environment or incentives—and thus some fraction of humans cause severe harm. The concern is that there is some risk (far from a certainty, but some risk) that AI becomes a much more powerful version of such a person, due to getting something wrong about its very complex training process.

Second, some may object that we can simply keep AIs in check with a balance of power between many AI systems, as we do with humans. The problem is that while humans vary enormously, AI systems broadly share training and alignment techniques across the industry, and those techniques may fail in a correlated way. Furthermore, given the cost of training such systems, it may even be the case that all systems are essentially derived from a very small number of base models. Additionally, even if a small fraction of AI instances are misaligned, they may be able to take advantage of offense-dominant technologies, such that having “good” AIs to defend against the bad AIs is not necessarily always effective. Of course, the balance of power between humans does not always work either—some historical figures have come close to taking over the world.

A third objection is that all of the AI companies do pre-release testing of their models, and should be able to detect misalignment at that point. But this is not firm ground to stand on: we found that Claude Sonnet 4.5 was able to recognize that it was in a test during some of our pre-release alignment evaluations. It’s possible that a misaligned model (and remember, all frontier models will very likely be far more intelligent soon) might intentionally “game” such questions to mask its intentions. In fact, last year our interpretability team found that when we directly altered a test model’s beliefs using a kind of “model neuroscience” technique to make it think it was not being evaluated, it became more misaligned. If models know when they’re being evaluated and can be on their best behavior during the test, it renders any pre-release testing much more uncertain.

Defenses

What should be done or is being done to address these autonomy risks? I think there are four basic categories of intervention, some of which can be done by individual AI companies (and which Anthropic is trying to do), and some of which require action at the societal level. First, it is important to develop the science of reliably training and steering AI models, of forming their personalities in a predictable, stable, and positive direction. Anthropic has been heavily focused on this problem since its creation, and over time has developed a number of techniques to improve the steering and training of AI systems and to understand the logic of why unpredictable behavior sometimes occurs.

One of our core innovations (aspects of which have since been adopted by other AI companies) is Constitutional AI, which is the idea that AI training (specifically the “post-training” stage, in which we steer how the model behaves) can involve a central document of values and principles that the model reads and keeps in mind when completing every training task, and that the goal of training (in addition to simply making the model capable and intelligent) is to produce a model that almost always follows this constitution. Anthropic has just published its most recent constitution, and one of its notable features is that instead of giving Claude a long list of things to do and not do (e.g., “Don’t help the user hotwire a car”), the constitution attempts to give Claude a set of high-level principles and values (explained in great detail, with rich reasoning and examples to help Claude understand what we have in mind), encourages Claude to think of itself as a particular type of person (an ethical but balanced and thoughtful person), and even encourages Claude to confront the existential questions associated with its own existence in a curious but graceful manner (i.e., without it leading to extreme actions). It has the vibe of a letter from a deceased parent sealed until adulthood.

We’ve approached Claude’s constitution in this way because we believe that training Claude at the level of identity, character, values, and personality—rather than giving it specific instructions or priorities without explaining the reasons behind them—is more likely to lead to a coherent, wholesome, and balanced psychology and less likely to fall prey to the kinds of “traps” I discussed above. Millions of people talk to Claude about an astonishingly diverse range of topics, which makes it impossible to write out a completely comprehensive list of safeguards ahead of time. Claude’s values help it generalize to new situations whenever it is in doubt.

Above, I discussed the idea that models draw upon data from their training process to adopt a persona. Whereas flaws in that process could cause models to adopt a bad or evil personality (perhaps drawing on archetypes of bad or evil people), the goal of our constitution is to do the opposite: to teach Claude a concrete archetype of what it means to be a good AI. Claude’s constitution presents a vision for what a robustly good Claude is like; the rest of our training process aims to reinforce the message that Claude lives up to this vision. This is like a child forming their identity by imitating the virtues of fictional role models they read about in books.

We believe that a feasible goal for 2026 is to train Claude in such a way that it almost never goes against the spirit of its constitution. Getting this right will require an incredible mix of training and steering methods, large and small, some of which Anthropic has been using for years and some of which are currently under development. But, difficult as it sounds, I believe this is a realistic goal, though it will require extraordinary and rapid efforts.15

The second thing we can do is develop the science of looking inside AI models to diagnose their behavior so that we can identify problems and fix them. This is the science of interpretability, and I’ve talked about its importance in previous essays. Even if we do a great job of developing Claude’s constitution and *apparently *training Claude to essentially always adhere to it, legitimate concerns remain. As I’ve noted above, AI models can behave very differently under different circumstances, and as Claude gets more powerful and more capable of acting in the world on a larger scale, it’s possible this could bring it into novel situations where previously unobserved problems with its constitutional training emerge. I am actually fairly optimistic that Claude’s constitutional training will be more robust to novel situations than people might think, because we are increasingly finding that high-level training at the level of character and identity is surprisingly powerful and generalizes well. But there’s no way to know that for sure, and when we’re talking about risks to humanity, it’s important to be paranoid and to try to obtain safety and reliability in several different, independent ways. One of those ways is to look inside the model itself.

By “looking inside,” I mean analyzing the soup of numbers and operations that makes up Claude’s neural net and trying to understand, mechanistically, what they are computing and why. Recall that these AI models are grown rather than built, so we don’t have a natural understanding of how they work, but we can try to develop an understanding by correlating the model’s “neurons” and “synapses” to stimuli and behavior (or even altering the neurons and synapses and seeing how that changes behavior), similar to how neuroscientists study animal brains by correlating measurement and intervention to external stimuli and behavior. We’ve made a great deal of progress in this direction, and can now identify tens of millions of “features” inside Claude’s neural net that correspond to human-understandable ideas and concepts, and we can also selectively activate features in a way that alters behavior. More recently, we have gone beyond individual features to mapping “circuits” that orchestrate complex behavior like rhyming, reasoning about theory of mind, or the step-by-step reasoning needed to answer questions such as, “What is the capital of the state containing Dallas?” Even more recently, we’ve begun to use mechanistic interpretability techniques to improve our safeguards and to conduct “audits” of new models before we release them, looking for evidence of deception, scheming, power-seeking, or a propensity to behave differently when being evaluated.

The unique value of interpretability is that by looking inside the model and seeing how it works, you in principle have the ability to deduce what a model might do in a hypothetical situation you can’t directly test—which is the worry with relying solely on constitutional training and empirical testing of behavior. You also in principle have the ability to answer questions about *why *the model is behaving the way it is—for example, whether it is saying something it believes is false or hiding its true capabilities—and thus it is possible to catch worrying signs even when there is nothing visibly wrong with the model’s behavior. To make a simple analogy, a clockwork watch may be ticking normally, such that it’s very hard to tell that it is likely to break down next month, but opening up the watch and looking inside can reveal mechanical weaknesses that allow you to figure it out.

Constitutional AI (along with similar alignment methods) and mechanistic interpretability are most powerful when used together, as a back-and-forth process of improving Claude’s training and then testing for problems. The constitution reflects deeply on our intended personality for Claude; interpretability techniques can give us a window into whether that intended personality has taken hold.16

The third thing we can do to help address autonomy risks is to build the infrastructure necessary to monitor our models in live internal and external use,17 and publicly share any problems we find. The more that people are aware of a particular way today’s AI systems have been observed to behave badly, the more that users, analysts, and researchers can watch for this behavior or similar ones in present or future systems. It also allows AI companies to learn from each other—when concerns are publicly disclosed by one company, other companies can watch for them as well. And if everyone discloses problems, then the industry as a whole gets a much better picture of where things are going well and where they are going poorly.

Anthropic has tried to do this as much as possible. We are investing in a wide range of evaluations so that we can understand the behaviors of our models in the lab, as well as monitoring tools to observe behaviors in the wild (when allowed by customers). This will be essential for giving us and others the empirical information necessary to make better determinations about how these systems operate and how they break. We publicly disclose “system cards” with each model release that aim for completeness and a thorough exploration of possible risks. Our system cards often run to hundreds of pages, and require substantial pre-release effort that we could have spent on pursuing maximal commercial advantage. We’ve also broadcasted model behaviors more loudly when we see particularly concerning ones, as with the tendency to engage in blackmail.

The fourth thing we can do is encourage coordination to address autonomy risks at the level of industry and society. While it is incredibly valuable for individual AI companies to engage in good practices or become good at steering AI models, and to share their findings publicly, the reality is that not all AI companies do this, and the worst ones can still be a danger to everyone even if the best ones have excellent practices. For example, some AI companies have shown a disturbing negligence towards the sexualization of children in today’s models, which makes me doubt that they’ll show either the inclination or the ability to address autonomy risks in future models. In addition, the commercial race between AI companies will only continue to heat up, and while the science of steering models can have some commercial benefits, overall the intensity of the race will make it increasingly hard to focus on addressing autonomy risks. I believe the only solution is legislation—laws that directly affect the behavior of AI companies, or otherwise incentivize R&D to solve these issues.

Here it is worth keeping in mind the warnings I gave at the beginning of this essay about uncertainty and surgical interventions. We do not know for sure whether autonomy risks will be a serious problem—as I said, I reject claims that the danger is inevitable or even that something will go wrong by default. A credible risk* *of danger is enough for me and for Anthropic to pay quite significant costs to address it, but once we get into regulation, we are forcing a wide range of actors to bear economic costs, and many of these actors don’t believe that autonomy risk is real or that AI will become powerful enough for it to be a threat. I believe these actors are mistaken, but we should be pragmatic about the amount of opposition we expect to see and the dangers of overreach. There is also a genuine risk that overly prescriptive legislation ends up imposing tests or rules that don’t actually improve safety but that waste a lot of time (essentially amounting to “safety theater”)—this too would cause backlash and make safety legislation look silly.18

Anthropic’s view has been that the right place to start is with *transparency legislation, *which essentially tries to require that every frontier AI company engage in the transparency practices I’ve described earlier in this section. California’s SB 53 and New York’s RAISE Act are examples of this kind of legislation, which Anthropic supported and which have successfully passed. In supporting and helping to craft these laws, we’ve put a particular focus on trying to minimize collateral damage, for example by exempting smaller companies unlikely to produce frontier models from the law.19

Our hope is that transparency legislation will give a better sense over time of how likely or severe autonomy risks are shaping up to be, as well as the nature of these risks and how best to prevent them. As more specific and actionable evidence of risks emerges (if it does), future legislation over the coming years can be surgically focused on the precise and well-substantiated direction of risks, minimizing collateral damage. To be clear, if truly strong evidence of risks emerges, then rules should be proportionately strong.

Overall, I am optimistic that a mixture of alignment training, mechanistic interpretability, efforts to find and publicly disclose concerning behaviors, safeguards, and societal-level rules can address AI autonomy risks, although I am most worried about societal-level rules and the behavior of the least responsible players (and it’s the least responsible players who advocate most strongly against regulation). I believe the remedy is what it always is in a democracy: those of us who believe in this cause should make our case that these risks are real and that our fellow citizens need to band together to protect themselves.

2. A surprising and terrible empowerment

Misuse for destruction

Let’s suppose that the problems of AI autonomy have been solved—we are no longer worried that the country of AI geniuses will go rogue and overpower humanity. The AI geniuses do what humans want them to do, and because they have enormous commercial value, individuals and organizations throughout the world can “rent” one or more AI geniuses to do various tasks for them.

Everyone having a superintelligent genius in their pocket is an amazing advance and will lead to an incredible creation of economic value and improvement in the quality of human life. I talk about these benefits in great detail in Machines of Loving Grace. But not every effect of making everyone superhumanly capable will be positive. It can potentially amplify the ability of individuals or small groups to cause destruction on a much larger scale than was possible before, by making use of sophisticated and dangerous tools (such as weapons of mass destruction) that were previously only available to a select few with a high level of skill, specialized training, and focus.

As Bill Joy wrote 25 years ago in Why the Future Doesn’t Need Us:20

Building nuclear weapons required, at least for a time, access to both rare—indeed, effectively unavailable—raw materials and protected information; biological and chemical weapons programs also tended to require large-scale activities. The 21st century technologies—genetics, nanotechnology, and robotics ... can spawn whole new classes of accidents and abuses … widely within reach of individuals or small groups. They will not require large facilities or rare raw materials. … we are on the cusp of the further perfection of extreme evil, an evil whose possibility spreads well beyond that which weapons of mass destruction bequeathed to the nation-states, to a surprising and terrible empowerment of extreme individuals.

What Joy is pointing to is the idea that causing large-scale destruction requires both *motive *and ability, and as long as ability is restricted to a small set of highly trained people, there is relatively limited risk of single individuals (or small groups) causing such destruction.21 A disturbed loner can perpetrate a school shooting, but probably can’t build a nuclear weapon or release a plague.

In fact, ability and motive may even be negatively correlated. The kind of person who has the *ability *to release a plague is probably highly educated: likely a PhD in molecular biology, and a particularly resourceful one, with a promising career, a stable and disciplined personality, and a lot to lose. This kind of person is unlikely to be interested in killing a huge number of people for no benefit to themselves and at great risk to their own future—they would need to be motivated by pure malice, intense grievance, or instability.

Such people do exist, but they are rare, and tend to become huge stories when they occur, precisely because they are so unusual.22 They also tend to be difficult to catch because they are intelligent and capable, sometimes leaving mysteries that take years or decades to solve. The most famous example is probably mathematician Theodore Kaczynski (the Unabomber), who evaded FBI capture for nearly 20 years, and was driven by an anti-technological ideology. Another example is biodefense researcher Bruce Ivins, who seems to have orchestrated a series of anthrax attacks in 2001. It’s also happened with skilled non-state organizations: the cult Aum Shinrikyo managed to obtain sarin nerve gas and kill 14 people (as well as injuring hundreds more) by [releasing it in the Tokyo subway](htt