I think this is a good description of what agent foundations is and why it might be needed. But the binary of 'either we get alignment by default or we need to find the True Name' isn't how I think about it.

Rather, there's some unknown parameter, something like 'how sharply does the pressure towards incorrigibility ramp up, what capability level does it start at, how strong is it'?

Setting this at 0 means alignment by default. Setting this higher and higher means we need various kinds of Prosaic alignment strategies which are better at keeping systems corri... (read more)

Like I said in my first comment, the in practice difficulty of alignment is obviously connected to timeline and takeoff speed.

But you're right that you're talking about the intrinsic difficulty of alignment Vs takeoff speed in this post, not the in practice difficulty.

But those are also still correlated, for the reasons I gave - mainly that a discontinuity is an essential step in Eleizer style pessimism and fast takeoff views. I'm not sure how close this correlation is.

Do these views come apart in other possible worlds? I.e. could you believe in a disconti... (read more)

three possibilities about AI alignment which are orthogonal to takeoff speed and timing

I think "AI Alignment difficulty is orthogonal to takeoff speed/timing" is quite conceptually tricky to think through, but still isn't true. It's conceptually tricky because the real truth about 'alignment difficulty' and takeoff speed, whatever it is, is probably logically or physically necessary: there aren't really alternative outcomes there. But we have a lot of logical uncertainty and conceptual confusion, so it still looks like there are different possibilities. St... (read more)

catastrophists: when evolution was gradually improving hominid brains, suddenly something clicked - it stumbled upon the core of general reasoning - and hominids went from banana classifiers to spaceship builders. hence we should expect a similar (but much sharper, given the process speeds) discontinuity with AI.

gradualists: no, there was no discontinuity with hominids per se; human brains merely reached a threshold that enabled cultural accumulation (and in a meaningul sense it was culture that built those spaceships). similarly, we should not expect sudd

Compare this,

[Shulman][22:18]  

We're in the Eliezerverse with huge kinks in loss graphs on automated programming/Putnam problems.

Not from scaling up inputs but from a local discovery that is much bigger in impact than the sorts of jumps we observe from things like Transformers.

[Yudkowsky][22:21]  

but, sure, "huge kinks in loss graphs on automated programming / Putnam problems" sounds like something that is, if not mandated on my model, much more likely than it is in the Paulverse. though I am a bit surprised because I would not have expected Paul

Summary of why I think the post's estimates are too low as estimates of what's required for a system capable of seizing a decisive strategic advantage:

To be an APS-like system OmegaStar needs to be able to control robots or model real world stuff and also plan over billions, not hundreds of action steps.

Each of those problems adds on a few extra OOMs that aren't accounted for in e.g. the setup for Omegastar (which can transfer learn across tens of thousands of games, each requiring thousands of action steps to win in a much less complicated environment tha... (read more)

Updates on this after reflection and discussion (thanks to Rohin):

Human Evolution tells us very little about the 'cognitive landscape of all minds' (if that's even a coherent idea) - it's simply a loosely analogous individual historical example

Saying Paul's view is that the cognitive landscape of minds might be simply incoherent isn't quite right - at the very least you can talk about the distribution over programs implied by the random initialization of a neural network.

I could have just said 'Paul doesn't see this strong generality attractor in the cogni... (read more)

Holden also mentions something a bit like Eliezer's criticism in his own write-up,

In particular, I think it's hard to rule out the possibility of ingenuity leading to transformative AI in some far more efficient way than the "brute-force" method contemplated here.

When Holden talks about 'ingenuity' methods that seems consistent with Eliezer's 

They're not going to be taking your default-imagined approach algorithmically faster, they're going to be taking an algorithmically different approach that eats computing power in a different way than you imagine

Also Climate Change itself doesn't completely not look like this scenario, same with nuclear deterrence.

isn't trying to do anything like "sketch a probability distribution over the dynamics of an AI project that is nearing AGI". This includes all technical MIRI papers I'm familiar with.

I think this specific scenario sketch is from a mainstream AI safety perspective a case where we've already failed - i.e. we've invented a useless corrigibility intervention that we confidently but wrongly think is scalable.

And if you try training the AI out of that habit in a domain of lower complexity and intelligence, it is predicted by me that generalizing that trained AI

One of the problems here is that, as well as disagreeing about underlying world models and about the likelihoods of some pre-AGI events, Paul and Eliezer often just make predictions about different things by default. But they do (and must, logically) predict some of the same world events differently.

My very rough model of how their beliefs flow forward is:

Paul

Low initial confidence on truth/coherence of 'core of generality'

→

Human Evolution tells us very little about the 'cognitive landscape of all minds' (if that's even a coherent idea) - it's simply a loo... (read more)

Great and extremely valuable discussion! There's one part that I really wished had been explored further - the fundamental difficulty of inner alignment:

Joe Carlsmith: I do have some probability that the alignment ends up being pretty easy. For example, I have some probability on hypotheses of the form "maybe they just do what you train them to do," and "maybe if you just don't train them to kill you, they won't kill you." E.g., in these worlds, non-myopic consequentialist inner misalignment doesn't tend to crop up by default, and it's not that hard to fin

And I think they are well enough motivated to stop their imminent annihilation, in a way that is more like avoiding mutual nuclear destruction than cosmopolitan altruistic optimal climate mitigation timing.

In my recent writeup of an investigation into AI Takeover scenarios I made an identical comparison - i.e. that the optimistic analogy looks like avoiding nuclear MAD for a while and the pessimistic analogy looks like optimal climate mitigation:

It is unrealistic to expect TAI to be deployed if first there are many worsening warning shots involving dangero

Some comments on the model

General

• In defining the rate of AI progress and other related variables, we’ve assumed the practical impact of AI on the economy and society scales up roughly with AI ‘intelligence’, and in general used these terms (intelligence and capability) interchangeably. We have then asked if the growth of intelligence might involve sudden jumps or accelerate hyperbolically. However, as Karnofsky points out, the assumption that generality of intelligence = capability is probably false.
• There isn’t a single variable that captures all the conce

Some points that didn't fit into the main post:

If the slow scenarios capture reality better than the fast scenarios, then systems will be deployed deliberately and will initially be given power rather than seizing power. This means both that the systems won’t be so obviously dangerous that the misbehaviour is noticed early on and that there is still misalignment later on. 

 This switch from apparently benign to dangerous behaviour could be due to

• Power-seeking misaligned behaviour that is too subtle to notice in the training environment but is obvi

On reflection, I think you're right, and his report does apply to a wider range of scenarios, probably all of the ones we discuss excluding the brain-in-a-box scenarios.

However, I think the report's understanding of power-seeking AI does assume a takeoff that is not extremely fast, such that we end up deliberately deciding to deploy the potentially dangerous AI on a large scale, rather than a system exploding in capability almost immediately.

Given the assumptions of the brain-in-a-box scenario many of the corrective mechanisms the report discusses wouldn't... (read more)

Some points that didn't fit into the main post:

While these scenarios do not capture alI of the risks from transformative AI, participants in a recent survey aimed at leading AI safety/governance researchers estimated the first three of these scenarios to cover 50% of existential catastrophes from AI.

The full survey results break down as 16 % 'Superintelligence' (i.e. some version of 'brain-in-a-box'), 16 % WFLL 2 and 18 % WFLL 1, for a total of 49% of the probability mass explicitly covered by our report (Note that these are all means of distributions over... (read more)

The 'one big breakthrough' idea is definitely a way that you could have easy marginal intelligence improvements at HLMI, but we didnt't call the node 'one big breakthrough/few key insights needed' because that's not the only way it's been characterised. E.g. some people talk about a 'missing gear for intelligence', where some minor change that isn't really a breakthrough (like tweaking a hyperparameter in a model training procedure) produces massive jumps in capability. Like David said, there's a subsequent post where we go through the different ways the jump to HLMI could play out, and One Big Breakthrough (we call it 'few key breakthroughs for intelligence) is just one of them.

I agree that that was his object-level claim about GPT-3 coding a react app - that it's relatively simple and coherent and can acquire lots of different skills via learning, vs being a collection of highly specialised modules. And of relevance to this post, the first is a way that intelligence improvements could be easy, and the second is the way they could be hard. Our 'interpretation' was more about making explicit what the observation about GPT-3 was,

GPT-3 is general enough that it can write a functioning app given a short prompt, despite the fact that

Perhaps this is a crux in this debate: If you think the 'agent-agnostic perspective' is useful, you also think a relatively steady state of 'AI Safety via Constant Vigilance' is possible. This would be a situation where systems that aren't significantly inner misaligned (otherwise they'd have no incentive to care about governing systems, feedback or other incentives) but are somewhat outer misaligned (so they are honestly and accurately aiming to maximise some complicated measure of profitability or approval, not directly aiming to do what we want them to ... (read more)

- They will not work in any environment outside of XLand (unless that environment looks very very similar to XLand).

In particular, I reject the idea that these agents have learned “general strategies for problem solving” or something like that, such that we should expect them to work in other contexts as well, perhaps with a little finetuning. I think they have learned general strategies for solving a specific class of games in XLand.

Strongly agree with this, although with the caveat that it's deeply impressive progress compared to the state of the art in ... (read more)

This is amazing. So it's the exact same agents performing well on all of these different tasks, not just the same general algorithm retrained on lots of examples. In which case, have they found a generally useful way around the catastrophic forgetting problem? I guess the whole training procedure, amount of compute + experience, and architecture, taken together, just solves catastrophic forgetting - at least for a far wider range of tasks than I've seen so far.

Could you use this technique to e.g. train the same agent to do well on chess and go?

I also notic... (read more)

Great post! I'm glad someone has outlined in clear terms what these failures look like, rather than the nebulous 'multiagent misalignment', as it lets us start on a path to clarifying what (if any) new mitigations or technical research are needed.

Agent-agnostic perspective is a very good innovation for thinking about these problems - is line between agentive and non-agentive behaviour is often not clear, and it's not like there is a principled metaphysical distinction between the two (e.g. Dennett and the Intentional Stance). Currently, big corporations ca... (read more)

Update to 'Modelling Continuous Progress'

I made an attempt to model intelligence explosion dynamics in this post, by attempting to make the very oversimplified exponential-returns-to-exponentially-increasing-intelligence model used by Bostrom and Yudkowsky slightly less oversimplified.

This post tries to build on a simplified mathematical model of takeoff which was first put forward by Eliezer Yudkowsky and then refined by Bostrom in Superintelligence, modifying it to account for the different assumptions behind continuous, fast progress as opposed to disco

Is a bridge falling down the moment you finish building it an extreme and somewhat strange failure mode? In the space of all possible bridge designs, surely not. Most bridge designs fall over. But in the real world, you could win money all day betting that bridges won't collapse the moment they're finished.

I'm not saying this is an exact analogy for AGI alignment - there are lots of specific technical reasons to expect that alignment is not like bridge building and that there are reasons why the approaches we're likely to try will break on us suddenly in w... (read more)

I agree with your argument about likelihood of DSA being higher compared to previous accelerations, due to society not being able to speed up as fast as the technology. This is sorta what I had in mind with my original argument for DSA; I was thinking that leaks/spying/etc. would not speed up nearly as fast as the relevant AI tech speeds up.

Your post on 'against GDP as a metric' argues more forcefully for the same thing that I was arguing for, that 

'the economic doubling time' stops being so meaningful - technological progress speeds up abruptly but o

Currently the most plausible doom scenario in my mind is maybe a version of Paul’s Type II failure. (If this is surprising to you, reread it while asking yourself what terms like “correlated automation failure” are euphemisms for.) 

This is interesting, and I'd like to see you expand on this. Incidentally I agree with the statement, but I can imagine both more and less explosive, catastrophic versions of 'correlated automation failure'. On the one hand it makes me think of things like transportation and electricity going haywire, on the other it could ... (read more)

Humans have skills and motivations (such as deception, manipulation and power-hungriness) which would be dangerous in AGIs. It seems plausible that the development of many of these traits was driven by competition with other humans, and that AGIs trained to answer questions or do other limited-scope tasks would be safer and less goal-directed. I briefly make this argument here.

Note that he claims that this may be true even if single/single alignment is solved, and all AGIs involved are aligned to their respective users.

It strikes me as interesting that muc... (read more)

Yeah - this is a case where how exactly the transition goes seems to make a very big difference. If it's a fast transition to a singleton, altering the goals of the initial AI is going to be super influential. But if it's that there are many generations of AIs that over time become the larger majority of the economy, then just control everything - predictably altering how that goes seems a lot harder at least.

Comparing the entirety of the Bostrom/Yudkowsky singleton intelligence explosion scenario to the slower more spread out scenario, it's not clear that... (read more)

That said, I remain interested in more clarity on what you see as the biggest risks with these multi/multi approaches that could be addressed with technical research.

A (though not necessarily the most important) reason to think technical research into computational social choice might be useful is that examining specifically the behaviour of RL agents from a computational social choice perspective might alert us to ways in which coordination with future TAI might be similar or different to the existing coordination problems we face.

(i) make direct improvem

Thanks for this long and very detailed post!

The MARL projects with the greatest potential to help are probably those that find ways to achieve cooperation between decentrally trained agents in a competitive task environment, because of its potential to minimize destructive conflicts between fleets of AI systems that cause collateral damage to humanity.  That said, even this area of research risks making it easier for fleets of machines to cooperate and/or collude at the exclusion of humans, increasing the risk of humans becoming gradually disenfranchi

Furthermore, we should take seriously the possibility that superintelligent AGIs might be even less focused than humans are on achieving large-scale goals. We can imagine them possessing final goals which don’t incentivise the pursuit of power, such as deontological goals, or small-scale goals. 

...

My underlying argument is that agency is not just an emergent property of highly intelligent systems, but rather a set of capabilities which need to be developed during training, and which won’t arise without selection for it

Was this line of argument inspire... (read more)

In terms of inferences about deceptive alignment, it might be useful to go back to the one and only current example we have where someone with somewhat relevant knowledge was led to wonder whether deception had taken place - GPT-3 balancing brackets. I don't know if anyone ever got Eliezer's $1000 bounty, but the top-level comment on that thread at least convinces me that it's unlikely that GPT-3 via AI Dungeon was being deceptive even though Eliezer thought there was a real possibility that it was.

Now, this doesn't prove all that much, but one thing it do... (read more)

The 'progress will be continuous' argument, to apply to our near future, does depend on my other assumptions - mainly that the breakthroughs on that list are separable, so agentive behaviour and long-term planning won't drop out of a larger GPT by themselves and can't be considered part of just 'improving up language model accuracy'.

We currently have partial progress on human-level language comprehension, a bit on cumulative learning, but near zero on managing mental activity for long term planning, so if we were to suddenly r... (read more)

So to sum up, a very high-level summary of the steps in this method of preference elicitation and aggregation would be:

1. With a mixture of normative assumptions and multi-channel information (approval and actions) as inputs, use a reward-modelling method to elicit the debiased preferences of many individuals.
1. Determining whether there actually are significant differences between stated and revealed preferences when performing reward modelling is the first step to using multi-channel information to effectively separate biases from preferences.
2. Create 'prox

I don't think that excuse works in this case - I didn't give it a 'long-winded frame', just that brief sentence at the start, and then the list of scenarios, and even though I reran it a couple of times on each to check, the 'cranberry/grape juice kills you' outcome never arose.

So, perhaps they switched directly from no prompt to an incredibly long-winded and specific prompt without checking what was actually necessary for a good answer? I'll point out didn't really attempt any sophisticated prompt programming either - that was literally the first sentence I thought of!

Gary Marcus, noted sceptic of Deep Learning, wrote an article with Ernest Davis:

GPT-3, Bloviator: OpenAI’s language has no idea what it’s talking about

The article purports to give six examples of GPT-3's failure - Biological, Physical, Social, Object and Psychological reasoning and 'non sequiturs'. Leaving aside that GPT-3 works on Gary's earlier GPT-2 failure examples, and that it seems as though he specifically searched out weak points by testing GPT-3 on many more examples than were given, something a bit odd is going... (read more)

Glad you think so! I think that methods like using multiple information sources might be a useful way to reduce the number of (potentially mistaken) normative assumptions you need in order to model a single human's preferences.

The other area of human preference learning where you seem, inevitably, to need a lot of strong normative assumptions is in preference aggregation. If we assume we have elicited the preferences of lots of individual humans, and we're then trying to aggregate their preferences (with each human's preference represented ... (read more)

Modelling the Human Trajectory or ‘How I learned to stop worrying and love Hegel’.

Rohin’s opinion: I enjoyed this post; it gave me a visceral sense for what hyperbolic models with noise look like (see the blog post for this, the summary doesn’t capture it). Overall, I think my takeaway is that the picture used in AI risk of explosive growth is in fact plausible, despite how crazy it initially sounds.

One thing this post led me to consider is that when we bring together various fields, the evidence for 'things will go insane in the next century' is stron... (read more)

Improving preference learning approaches

When examining value learning approaches to AI Alignment, we run into two classes of problem - we want to understand how to elicit preferences, which is (even theoretically, with infinite computing power), very difficult, and we want to know how to go about aggregating preferences stably and correctly which is not just difficult but runs into complicated social choice and normative ethical issues.

Many research programs say the second of these questions is less important than the first, especially if we expect continu... (read more)

To get around the impossibility result, we need "normative assumptions": assumptions about the preferences (or beliefs, or biases) of the agent that cannot be deduced fully from observations.

Under the optimistic scenario, we don't need many of these, at least for identifying human preferences. We can label a few examples ("the anchoring bias, as illustrated in this scenario, is a bias"; "people are at least weakly rational"; "humans often don't think about new courses of action they've never s

‘You get what you measure’ (outer alignment failure) and Mesa optimisers (inner failure) are both potential gap fillers that explain why specifically the alignment/capability divergence initially arises. Whether it’s one or the other, I think the overall point is still that there is this gap in the classic arguments that allows for a (possibly quite high) chance of ‘alignment by default’, for the reasons you give, but there are at least 2 plausible mechanisms that fill this gap. And then I suppose my broader point would be that we should present:

Classic Arguments —> objections to them (capability and alignment often go together, could get alignment by default) —> specific causal mechanisms for misalignment

I think what you've identified here is a weakness in the high-level, classic arguments for AI risk -

Overall, I’d give maybe a 10-20% chance of alignment by this path, assuming that the unsupervised system does end up with a simple embedding of human values. The main failure mode I’d expect, assuming we get the chance to iterate, is deception - not necessarily “intentional” deception, just the system being optimized to look like it’s working the way we want rather than actually working the way we want. It’

I wrote a whole post on modelling specific continuous or discontinuous scenarios- in the course of trying to make a very simple differential equation model of continuous takeoff, by modifying the models given by Bostrom/Yudkowsky for fast takeoff, the result that fast takeoff means later timelines naturally jumps out.

Varying d between 0 (no RSI) and infinity (a discontinuity) while holding everything else constant looks like this: If we compare the trajectories, we see two effects - the more continuous the progress is (lower d), the earlier we see growt

Inner Alignment / Misalignment is possibly the key specific mechanism which fills a weakness in the 'classic arguments' for AI safety - the Orthogonality Thesis, Instrumental Convergence and Fast Progress together implying small separations between AI alignment and AI capability can lead to catastrophic outcomes. The question of why there would be such a damaging, hard-to-detect divergence between goals and alignment needs an answer to have a solid, specific reason to expect dangerous misalignment, and Inner Misalignment is just such a reason.

I t... (read more)

--The orthogonality thesis and convergent instrumental goals arguments, respectively, attacked and destroyed two views which were surprisingly popular at the time: 1. that smarter AI would necessarily be good (unless we deliberately programmed it not to be) because it would be smart enough to figure out what's right, what we intended, etc. and 2. that smarter AI wouldn't lie to us, hurt us, manipulate us, take resources from us, etc. unless it wanted to (e.g. because it hates us, or because it has been programmed to kill, etc) which it pr

What would you say is wrong with the 'exaggerated' criticism?

I don't think you can call the arguments wrong if you also think the Orthogonality Thesis and Instrumental Convergence are real and relevant to AI safety, and as far as I can tell the criticism doesn't claim that - just that there are other assumptions needed for disaster to be highly likely.

I find this interesting in the context of the recent podcast on errors in the classic arguments for AI risk - which boil down to, there is no necessary reason why instrumental convergence or orthogonality apply to your systems, and there are actually strong reasons, a priori, to think increasing AI capabilities and increasing AI alignment go together to some degree... and then GPT-3 comes along, and suggests that, practically speaking, you can get highly capable behaviour that scales up easily without much in the way of alignment.

On the one hand, GPT-3 is ... (read more)