Definition. On how I use words, values are decision-influences (also known as shards). “I value doing well at school” is a short sentence for “in a range of contexts, there exists an influence on my decision-making which upweights actions and plans that lead to e.g. learning and good grades and honor among my classmates.” 

Summaries of key points:

  1. Nonrobust decision-influences can be OK. A candy-shard contextually influences decision-making. Many policies lead to acquiring lots of candy; the decision-influences don't have to be "globally robust" or "perfect."
  2. Values steer optimization; they are not optimized against. The value shards aren't getting optimized hard. The value shards are the things which optimize hard, by wielding the rest of the agent's cognition (e.g. the world model, the general-purpose planning API). 

    Since values are not the optimization target of the agent with those values, the values don't have to be adversarially robust.
  3. Since values steer cognition, reflective agents try to avoid adversarial inputs to their own values. In self-reflective agents which can think about their own thinking, values steer e.g. what plans get considered next. Therefore, these agents convergently avoid adversarial inputs to their currently activated values (e.g. learning), because adversarial inputs would impede fulfillment of those values (e.g. lead to less learning).

Follow-up to: Don't design agents which exploit adversarial inputs, Don't align agents to evaluations of plans

I: Nonrobust decision-influences can be OK

Decision-making influences don't have to be “robust” in order for a person to value doing well at school. Consider two people with slightly different values:

  1. One person is slightly more motivated by good grades. They might study for a physics test and focus slightly more on test-taking tricks. 
  2. Another person is slightly more motivated by learning. They might forget about some quizzes because they were too busy reading extracurricular physics books. 

But they might both care about school, in the sense of reliably making decisions on the basis of their school performance, and valuing being a person who gets good grades. Both people are motivated to do well at school, albeit in somewhat different ways. They probably will both get good grades, and they probably will both learn a lot. Different values simply mean that the two people locally make decisions differently.

If I value candy, that means that my decision-making contains a subroutine which makes me pursue candy in certain situations. Perhaps I eat candy, perhaps I collect candy, perhaps I let children tour my grandiose candy factory… The point is that candy influences my decisions. I am pulled by my choices from pasts without candy to futures with candy.

So, let  be the set of mental contexts relevant for decision-making, and let  be my action set.[1] My policy has type signature , and e.g. contains a bunch of shards of value which influence its outputs. The values are subcircuits of my policy network (i.e. my brain). For example, consider a candy shard consisting of the following subshards:

  1. If center-of-visual-field activates candy’s visual abstraction, then grab the inferred latent object which activated the abstraction.
  2. If hunger>50 and sugar-level<6, and if current-plan-stub activates candy-obtainable, then tell planning API to set subgoal to obtain candy.
  3. If heard 'candy' and hunger>20, then salivate.

Suppose this is the way I value candy. A few thousand subshards which chain into the rest of my cognition and concepts. A few thousand subshards of value which were hammered into place by tens of thousands of reinforcement events across a lifetime of experience. 

This shard does not need to be “robust” or "perfect." Am I really missing much if I’m lacking candy subshard #3: “If heard 'candy' and hunger>20, then salivate”? I don’t think it makes sense to call value shards “perfect” or not.[2] The shards simply influence decisions. 

There are many, many configurations and parameter settings of these subshards which lead to valuing candy. The person probably still values candy, even if you: 

  • Delete a bunch of the subshards.
  • Modify the activation-strength of a bunch of subshards (roughly, change how much control the subshard has on the next-thought "logits"). 
  • Change some of the activation contexts to other common activation contexts (e.g. "If heard 'candy'" changes to "If heard 'sweets'", change to hunger>14 in subshard 3).

It seems to me like "does the person still prioritize candy" depends on a bunch of factors, including:

  1. Retention of core abstractions (to some tolerance)
    1. If we find-replaced candy with flower, the person probably now has a strange flower-value, where they eat flowers when hungry.
    2. However, the abstraction also doesn't have to be "perfect" (whatever that means) in order to activate in everyday situations. Two people will have different candy abstractions, and yet they can both value candy.
  2. Strength and breadth of activation contexts
    1. The more situations a candy-value affects decision-making in, the stronger the chance that candy remains a big part of their life.
  3. How often the candy shard will actually activate
    1. As an unrealistic example, if the person never enters a cognitive situation which substantially activates the candy-shard, then don't expect them to eat much candy. 
    2. This is another source of value/decision-influence robustness, as e.g. an AI's values don't have to be OK in every cognitive context.[3] 
    3. Consider an otherwise altruistic man who has serious abuse and anger problems whenever he enters a specific vacation home with his wife, but is otherwise kind and considerate. As long as he doesn't start off in that home but knows about the contextual decision-influence, he will steer away from that home and try to remove the unendorsed value.
  4. Reflectivity of the candy shard
    1. (This is more complicated and uncertain. I'll leave it for now.)

Suppose we wanted to train an agent which gets really smart and acquires a lot of candy, now and far into the future. That agent's decision-influences don't have to be globally robust (e.g. in every cognitive situation, the agent is motivated by candy and only by candy) in order for an agent to make locally good decisions (e.g. make lots of candy now and into the future).

II: Values steer optimization; they are not optimized against

Given someone’s values, you might wonder if you can “maximize” those values. On my ontology—where values are decision-influences, a sort of contextual wanting“literal value maximization” is a type error.[4] In particular, given e.g. someone who values candy, there very probably isn't a part of that person's cognition which can be argmaxed to find a plan where the person has lots of candy. 

So if I have a candy-shard, if I value candy, if I am influenced to decide to pursue candy in certain situations, then what does it mean to maximize my candy value? My value is a subcircuit of my policy. It doesn’t necessarily even have an ordering over its outputs, let alone a numerical rating which can be maximized. “Maximize my candy-value” is, in a literal sense, a type error. What quantity is there to maximize? 

the True Name of a thing [is] a mathematical formulation sufficiently robust that one can apply lots of optimization pressure without the formulation breaking down[...]

If we had the “True Name” of human values (insofar as such a thing exists), that would potentially solve the problem [of supervised labels only being proxies for what we want].

Why Agent Foundations? An Overly Abstract Explanation

In particular, there’s no guarantee that you can just scan someone’s brain and find some True Name of Value which you can then optimize without fear of Goodhart. It’s not like we don’t know what people value, but if we did, we would be OK. I'm pretty confident there does not exist anything within my brain which computes a True Name for my values, ready to be optimized as hard as possible (relative to my internal plan ontology) and yet still producing a future where I get candy.

Therefore, even though you truly care about candy, that doesn’t mean you can just whip out the argmax on the relevant shard of your cognition, so as to “maximize” that shard (e.g. via extremizing the rate of action potentials on its output neurons) and then get a future with lots of candy. You’d probably just find a context  which acts as an adversarial input to the candy-shard, even though you do really care about candy in a normal, human way.

Complexity of human values isn’t what stops you from argmaxing human values and thereby finding a good plan. That’s not a sensible thing to try. Values are not, in general, the kind of thing which can be directly optimized over, where you find plans which "maximally activate" your e.g. candy-subshards. Values influence decisions.  

If you're confused at the distinction between "optimizing against values" and "values influencing decisions", read Don't align agents to evaluations of plans.

There is real difficulty and peril in motivating an AI, in making sure its decisions chain into each other towards the right kinds of futures. If you train a superintelligent sovereign agent which primarily values irrelevant quantities (like paperclips) but doesn't care about you, which then optimizes the whole future hard, then you’re dead. But consider that deleting candy subshard #3 (“If heard 'candy' and hunger>20, then salivate”) doesn’t stop someone from valuing candy in the normal way. If you erase that subshard from their brain, it’s not like they start "Goodharting" and forget about the “true nature” of caring about candy because they now have an “imperfect proxy shard.” 

An agent argmax'ing an imperfect evaluation function will indeed exploit that function; there are very few degrees of freedom in specifying an inexploitable evaluation function. But that's because that grading function must be globally robust. 

When I talk about shard theory, people often seem to shrug and go "well, you still need to get the values adversarially-robustly-correct else Goodhart; I don't see how this 'value shard' thing helps." That's not how values work, that is not what value-shards are. Unlike grader-optimizers which try to maximize plan evaluations, a values-executing agent doesn't optimize its values as hard as possible. The agent's values optimize the world. The values are rules for how the agent acts in relevant contexts.[5] 

III: Since values steer cognition, reflective agents try to avoid adversarial inputs to their own values

Question: If we cannot robustly grade expected-diamond-production for every plan the agent might consider, how might we nonetheless design a smart agent which makes lots of diamonds?

(Maybe you can now answer this question. I encourage you to try before moving on.)


In Don't design agents which exploit adversarial inputs, I wrote:

Imagine a mother whose child has been goofing off at school and getting in trouble. The mom just wants her kid to take education seriously and have a good life. Suppose she had two (unrealistic but illustrative) choices. 

  1. Evaluation-child: The mother makes her kid care extremely strongly about doing things which the mom would evaluate as "working hard" and "behaving well."
  2. Value-child: The mother makes her kid care about working hard and behaving well.

To make evaluation-child work hard, we have to somehow specify a grader which can adequately grade all plans which evaluation-child can imagine. The highest-rated imaginable plan must involve working hard. This requirement is extreme.

Value-child doesn't suffer this crippling "robustly grade exponentially many plans" alignment requirement. I later wrote a detailed speculative account of how value-child's cognition might work—what it means to say that he "cares about working hard." But, at a higher level, what are the main differences between evaluation- and value-child?

This may sound obvious, but I think that the main difference is that value-child actually cares about working hard. Evaluation-child cares about evaluations. (See here if confused on the distinction.) To make evaluation-child work hard in the limit of intelligence, you have to robustly ensure that max evaluations only come from working hard. This sure sounds like a slippery and ridiculous kind of thing to try, like wrestling a frictionless pig. It should be no surprise you'll hit issues like nearest unblocked strategy in that paradigm.

An agent which does care about working hard will want to not think thoughts which lead to not working hard. In particular, reflective shard-agents can think about what to think, and thereby are convergently-across-values incentivized to steer clear of adversarial inputs to their own values.

Reflectively avoiding adversarial inputs to your thinking

Reflective agents can think about their own thought process (e.g. "should I spend another five minutes thinking about what to write for this section?"). I think they do this via their world-model predicting internal observables (e.g. future neuron activations) and thus high-level statistics like "If I think for 5 more minutes, will that lead to a better post or not?". 

Thoughts about future thinking are a kind of decision. Decisions are steered by values. Therefore, thoughts about future thinking are steered by whatever value shards activate in that mental context. For example, a self-care value might activate, and a learning-shard, and a social value might activate as well. They control your reflective thoughts, just like other shards would control your ("normal") actions (like crossing the room). 

In Don't design agents which exploit adversarial inputs, I wrote: 

[In] the optimizer's curse, evaluations (eg "In this plan, how hard is evaluation-child working? Is he behaving?") are often corrupted by the influence of unendorsed factors (eg the attractiveness of the gym teacher caused an upwards error in the mother's evaluation of that plan). If you make choices by considering  options and then choosing the highest-evaluated one, then the more  increases, the harder you are selecting for upwards errors in your own evaluation procedure.

The proposers of the Optimizer's Curse also described a Bayesian remedy in which we have a prior on the expected utilities and variances and we are more skeptical of very high estimates. This however assumes that the prior itself is perfect, as are our estimates of variance. If the prior or variance-estimates contain large flaws somewhere, a search over a very wide space of possibilities would be expected to seek out and blow up any flaws in the prior or the estimates of variance.

Goodhart's Curse, Arbital

As far as I know, it's indeed not possible to avoid the curse in full generality, but it doesn't have to be that bad in practice. If I'm considering three research directions to work on next month, and I happen to be grumpy when considering direction #2, then maybe I don't pursue that direction. Even though direction #2 might have seemed the most promising under more careful reflection. I think that the distribution of plans I consider involves relatively small upwards errors in my internal evaluation metrics. Sure, maybe I occasionally make a serious mistake due to the optimizer's curse due to upwards "corruption", but I don't expect to literally die from the mistake. 

Thus, there are are degrees to the optimizer's curse.

Both grader-optimization and argmax cause extreme, horrible optimizer's curse. Is alignment just that hard? I think not.

The distribution of plans which I usually consider is not going to involve any set of mental events like "consider in detail building a highly persuasive superintelligence which persuades you to build it." While a reflective diamond-valuing AI which did execute the plan's mental steps might get hacked by that adversarial input, there would be no reason for it to seek out that plan to begin with. 

The diamond-valuing AI would consider a distribution of plans far removed from the extreme upwards errors highlighted in the evaluation-child story. (I think that this is why you, in your day-to-day thinking, don't have to worry about plans which are extreme adversarial inputs to your own evaluation procedures.) Even though a smart reflective AI may be implicitly searching over a range of plans, it's doing so reflectively, thinking about what to think next, and perhaps not taking cognitive steps which it reflectively predicts to lead to bad outcomes (e.g. via the optimizer's curse). 

On the other hand, an AI which is aligned on the evaluation procedure is incentivized to seek out huge upwards errors on the evaluation procedure relative to the intended goal. The actor is trying to generate plans which maximally exploit the grader's reasoning and judgment.[6]

Thus, if an AI cares about diamonds (i.e. has an influential diamond-shard), that AI might accidentally select a plan due to upwards evaluative noise, but that does not mean the AI is actively looking for plans to fool its diamond-shard into oblivion. The AI may make a mistake in its reflective predictions, but there's no extreme optimization pressure for it to make mistakes like that, and the AI wants to avoid those mistakes, and so those mistakes remain unlikely. I think that reflective, smart AIs convergently want to avoid duping their own evaluative procedures, for the same reasons you want to avoid doing that to yourself.

More precisely:

  1. A reflective diamond-motivated agent chooses plans based on how many diamonds they lead to. 
  2. The agent can predict e.g. how diamond-promising it is to search for plans involving simulating malign superintelligences which trick the agent into thinking the simulation plan makes lots of diamonds, versus plans where the agent just improves its synthesis methods.
  3. A reflective agent thinks that the first plan doesn't lead to many diamonds, while the second plan leads to more diamonds. 
  4. Therefore, the reflective agent chooses the second plan over the first plan, automatically[7] avoiding the worst parts of the optimizer's curse. (Unlike grader-optimization, which seeks out adversarial inputs to the diamond-motivated part of the system.)

Therefore, avoiding the high-strength curse seems conceptually straightforward. In the case of aligning an AI to produce lots of diamonds, we want the AI to superintelligently generate and execute diamond-producing plans because the AI expects those plans to lead to lots of diamonds. I have spelled out a plausible-to-me story for how to accomplish this. The story is simple in its essential elements: finetune a pretrained model by rewarding it when it collects diamonds.

While that story has real open questions, that story also totally sidesteps the problems with grader-optimization. You don't have to worry about providing some globally unhackable evaluation procedure to make super duper sure the agent's plans "really" involve diamonds. If the early part of training goes as described, the agent wants to make diamonds, and (as I explained in the diamond-alignment story) it reflectively wants to avoid duping itself because duping itself leads to fewer diamonds. 

This answers the above question:

If we cannot robustly grade expected-diamond-production for every plan the agent might consider, how might we nonetheless design a smart agent which makes lots of diamonds?

A reflective agent wishes to minimize the optimizer's curse (relative to its own values), instead of maximizing it (relative to the goal by which the grader evaluates plans). While I don't yet have satisfying pseudocode for reflective planning agents (but see Appendix B for preliminary pseudocode, effective reflective agents do exist. In this regime, it seems like many scary problems go away and don't come back. That is an enormous blessing.[8]

Argmax is an importantly inappropriate idealization of agency

If the answer to "how do we dispel the max-strength optimizer's curse" is in fact "real-world reflective agents do this naturally", then assuming unreflectivity will rule out the part of solution-space containing the actual solution:

As a further-simplified but still unsolved problem, an unreflective diamond maximizer is a diamond maximizer implemented on a Cartesian hypercomputer in a causal universe that does not face any Newcomblike problems. This further avoids problems of reflectivity and logical uncertainty. In this case, it seems plausible that the primary difficulty remaining is just the ontology identification problem

Diamond Maximizer, Arbital (emphasis added)

The argmax and unreflectivity assumptions were meant to make the diamond-maximizer problem easier. Ironically, however, these assumptions may well render the diamond-maximizer problem unsolvable, leading us to resort to increasingly complicated techniques and proposals, none of which seem to solve "core" problems like evaluation-rule hacking... 

Conclusion

  1. Nonrobust decision-influences can be OK. 
  2. Values steer optimization; they are not optimized against
  3. Since values steer cognition, reflective agents try to avoid adversarial inputs to their own values. 

The answer is not to find a clever way to get a robust grader. The answer is to not need a robust grader. Form e.g. a diamond-production value within a reflective and smart agent, and this diamond-production value won't be incentivized to fool itself. You won't have to "robustly grade" it to make it produce diamonds. 

Thanks to Tamera Lanham, John Wentworth, Justis Mills, Erik Jenner, Johannes Treutlein, Quintin Pope, Charles Foster, Andrew Critch, randomwalks, Ulisse Mini, and Garrett Baker for thoughts. Thanks to Vivek Hebbar for in-person discussion.

Appendix A: Several roads lead to a high-strength optimizer's curse

  1. Uncertainty about how human values work. Suppose we think that human values are so complex, and there's no real way to understand them or how they get generated. We imagine a smart AI as finding futures which optimize some grading rule, and so we need something to grade those futures. We think we can't get the AI to grade the futures, because human values are so complex. What options remain available? Well, the only sources of "good judgment" are existing humans, so we need to find some way to use those humans to target the AI's powerful cognition. We give the alignment, the AI gives the cognitive horsepower. 

    We've fallen into the grader-optimization trap. 
  2. Non-embedded forms of agency. This encourages considering a utility function maximized over all possible futures. Which automatically brings the optimizer's curse down to bear at maximum strength. You can't specify a utility function which is robust against that

    This seems sideways of real-world alignment, where realistic motivations may not be best specified in the form of "utility function over observation/universe histories."  

Appendix B: Preliminary reflective planning pseudocode

I briefly took a stab at writing pseudocode for a values-based agent like value-child. I think this code leaves a lot out, but I figured it'd be better to put something here for now.

'''
Here is one meta-plan for planning. The agent starts from no plan at all, iteratively generates improvements, which get accepted if they lead to more predicted diamonds. Depending on the current situation (as represented in the WM), the agent might execute a plan in which it looks for nearby diamonds, or it might execute a plan where it runs a different kind of heuristic search on a certain class of plans (e.g. research improvements to the AI's diamond synthesis pathway).

Any real shard agent would be reasoning and updating asynchronously, so this setup assumes a bit of unrealism.

This function only modifies the internal state of the agent (self.recurrent), so as to be ready for a call of self.getDecisions().
'''
def plan(self):
# Generate an initial plan
plan = Plan() # Do nothing plan
conseq = self.WM.getConseq(plan)
currentPlanEval = self.diamondShard(conseq)

# Iteratively modify the plan until the generative model can't find a way to make it better
while True:
 # Sample 5 plan modifications from generative model
 plans = self.WM.planModificationSample(n=5,stub=plan) 
 
 # Select first local improvement
 for planMod in plans:
  # Reflectively predict consequences of this plan
  newPlan = plan.modify(planMod) 
  conseq = self.WM.getConseq(plan) 
  
  # Take local improvement
  if self.diamondShard(conseq) > currentPlanEval: 
   plan = newPlan
   currentPlanEval = self.diamondShard(conseq)
   continue # Generate more modifications
 # Execute the plan, which possibly involves running plan search with a different algorithm and plan initialization.
 isDone = plan.exec() 
 if isDone: break

Appendix C: Value shards all the way down

I liked Vivek Hebbar's recent comment (in the context of e.g. caring about your family and locally evaluating plans on that basis, but also knowing that your evaluation ability itself is compromised and will mis-rate some plans):

My attempt at a framework where "improving one's own evaluator" and "believing in adversarial examples to one's own evaluator" make sense:

  • The agent's allegiance is to some idealized utility function  (like CEV).  The agent's internal evaluator  is "trying" to approximate  by reasoning heuristically.  So now we ask Eval to evaluate the plan "do argmax w.r.t. Eval over a bunch of plans".  Eval reasons that, due to the the way that Eval works, there should exist "adversarial examples" that score very highly on Eval but low on .  Hence, Eval concludes that  is low, where plan = "do argmax w.r.t. Eval".  So the agent doesn't execute the plan "search widely and argmax".
  • "Improving " makes sense because Eval will gladly replace itself with  if it believes that  is a better approximation for  (and hence replacing itself will cause the outcome to score better on )

Are there other distinct frameworks which make sense here?  

(I'm not sure whether Vivek meant to imply "and this is how I think people work, mechanistically." I'm going to respond to a hypothetical other person who did in fact mean that.)

My take is that human value shards explain away the need to posit alignment to an idealized utility function. A person is not a bunch of crude-sounding subshards (e.g. "If food nearby and hunger>15, then be more likely to go to food") and then also a sophisticated utility function (e.g. something like CEV). It's shards all the way down, and all the way up.[10] 

Vivek then wrote:

I look forward to seeing what design Alex proposes for "value child".

Value shards steer cognition. In the main essay, I wrote:

  1. A reflective diamond-motivated agent chooses plans based on how many diamonds they lead to. 
  2. The agent can predict e.g. how diamond-promising it is to search for plans involving simulating malign superintelligences which trick the agent into thinking the simulation plan makes lots of diamonds, versus plans where the agent just improves its synthesis methods.
  3. A reflective agent knows that the first plan doesn't lead to many diamonds, while the second plan leads to more diamonds. 
  4. Therefore, the reflective agent chooses the second plan over the first plan, automatically avoiding the worst parts of the optimizer's curse. (Unlike grader-optimization, which seeks out adversarial inputs to the diamond-motivated part of the system.)

This story smoothly accomodates thoughts about improving evaluation ability.

On my understanding: Your values are steering the optimization. They are not, in general, being optimized against by some search inside of you. They are probably not pointing to some idealized utility function. The decision-influences are guiding the search. There's no secret other source of caring, no externalized utility function. 

  1. ^

    Formalizing the action space  is a serious gloss. In people, there is no privileged “action” space, considering how I can decide what to think about next. As an embedded agent, I don’t just decide what motor commands to send and what words to say—I also can decide what to decide next, what to think about next. 

    I think the point of the essay stands anyways.

  2. ^

    This doesn’t mean that I’m using words the same way other people have, when deliberating on whether an AI’s values have to be “robust.” I’m more inclined to just carry out the shard theory analysis and see what experiences it leads me to anticipate, instead of arguing about whether my way of using words matches up with how other people have used words.

  3. ^

    As Charles Foster notes:

    This isn't entirely on the side of robustness. It also means that by default, even if we get the AI to have an X decision influence in one context, that doesn't necessarily also activate in another context we might want it to generalize to.

  4. ^

    I think that many people say "maximize my values" to mean something like "do something as great as possible, relative to what I care about." So, in a sense, "type error" is pedantic. But also I think the type error complaint points at something important, so I'll say it anyways.

  5. ^

    If you want to argue that decision-influences have to be robust else Goodhart, you need new arguments not related to grader-optimization. It is simply invalid to say "The agent doesn't value diamonds in some situation where lots of its values activate strongly, and therefore the agent won't make diamonds because it Goodharts on that unrelated situation." That is not what values do.

  6. ^

    In a recent Google Doc thread, grader optimization came up. Someone said to me (my reactions in italics):

    So you're imagining something like: the agent (policy) is optimizing for a reward model to produce a high number, and so the agent analyzes the reward model in detail to search for inputs that cause the reward model to give high numbers? Yes.

    I think at that level of generality I don't know enough to say whether this is good or bad. I think this is very, very probably bad.

    We want our AI system to search for approaches that better enact our values. As you note, the optimizer's curse says that we'll tend to get approaches that overestimate how much they actually enact our values. But just knowing that the optimizer's curse will happen doesn't change anything; the best course of action is still to take the approach that is predicted to best enact our values. In that sense, the optimizer's curse is typically something you have to live with, not something you can solve.[...] 

    A small error is not the same as a maximal error. Reflective agents can and will avoid deliberately searching for plans which maximize upwards errors in their own evaluations (e.g. generating a plan such that, while considering the plan, a superintelligence inside the plan tricks you into thinking the plan should be highly evaluated), because the agents reflectively predict that that hurts their goal achievement (e.g. leads to fewer diamonds). If you somewhat understand your decision-making, you can consider plans you're less likely to incorrectly evaluate. 



    So my followup question is: can you name a single approach that doesn't have this failure mode, while still allowing us to use the AI to do things we didn't think about in advance? Yes

    One answer someone might give is "create an agent-with-shards that searches for approaches that score highly on the shard. 

    Insofar as this means "the agent looks for inputs which maximize the aggregate shard output", no. On my model, shards grade and modify plans, including plans about which plans to consider next. They are not searching for plans which maximize evaluative output, like in the reward-model case. 

     

    An agent that searches for high scores on its shard can't be searching for positive upwards errors in the shard; there is no such thing as an error in the shard". To which the response is "that's from the agent's perspective. From the human's perspective, the agent is searching for positive upwards differences between the shards and what-the-human-wants". 

    Even if true, this would be not be an optimizer's curse problem.

    But also this isn't true, at least not without further argumentation. If my kid likes mocha and I like latte, is my child searching for positive upwards differences between their values and mine? I think there are some situations—AI paperclips, humans values love—where the AI is searching for paperclippish plans, which will systematically be bad plans by human lights. That seems more like instrumental convergence -> disempower humans -> not much love left for us if we're dead.

  7. ^

    I do think that e.g. a diamond-shard can get fed an adversarial input, but the diamond-shard won't bid for a plan where it fools itself.

  8. ^

    It's at this point that my model of Nate Soares wants to chime in.

    Alex's model of Nate (A-N): This sure smells like a problem redefinition, where you simply sweep the hard part of the problem under a less obvious corner of the rug. Why shouldn't I believe you've just done that?

    A: A reasonable and productive heuristic in general, but inappropriate here. Grader-optimization explicitly incentivizes the agent to find maximal upwards errors in a diamond-evaluation module, whereas a reflective diamond-valuing agent has no incentive to consider such plans, because it reflectively predicts those plans don't lead to diamonds. If you disagree, please point to the part of the story where, conditional on the previous part of the story obtaining, the grader-optimization problem reappears.

    A-N: Suppose we achieved your dream of forming a diamond-shard in an AI, and that that shard holds significant power over the AI's decisions. Now the AI keeps improving itself. Doesn't "get smarter" look a lot like "implicitly consider more options", which brings the curse back?

    A: If the agent is diamond-aligned at this point in time, I expect it stays that way for the reasons given in the "agent prevents value drift" section, along with these footnotes and the appendix. As a specific answer, though: If the agent does care about diamonds at that point it time, then it doesn't want to get so "smart" that it deludes itself by seriously intensifying the optimizer's curse. It doesn't want to do so for the reason we don't want it to do so (in the hypothetical where we just want to achieve diamond-alignment). If the reflective agent can predict that outcome of the plan, it won't execute the plan, because that plan leads to fewer diamonds

    A-N: So the AI still has to solve the AI alignment problem, except with its successors.

    A: Not all things which can be called an "AI alignment problem" are created equal. The AI has a range of advantages, and I detailed one way it could use those advantages. I do expect that kind of plan to actually work.

  9. ^

    I further speculate that reflective reasoning is convergently developed in real-world training processes under non-IID conditions like those described in my diamond-alignment story.

  10. ^

    When working out shard theory with Quintin Pope, one of my favorite moments was the click where I stopped viewing myself as some black-box optimizing "some complicated objective." Instead, this hypothesis reduced my own values to mere reality. Every aspiration, every unit of caring, every desire for how I want the future to be bright and fun—subroutines, subshards, contextual bits of decision-making influence, all traceable to historical reinforcement and update events. 

27

New Comment
27 comments, sorted by Click to highlight new comments since: Today at 11:43 AM

Values steer optimization; they are not optimized against

I strongly disagree with the implication here. This statement is true for some agents, absolutely. It's not true universally.

It's a good description of how an average human behaves most of the time, yes. We're often puppeted by our shards like this, and some people spend the majority of their lives this way. I fully agree that this is a good description of most of human cognition, as well.

But it's not the only way humans can act, and it's not when we're at our most strategically powerful.

Consider if the value-child gets thrown in a completely alien context. Like, in-person school gets replaced with remote self-learning due to a pandemic and he moves to live for a while on a tropical island with his grandmother, who never disciplines him. Basically all of the shards that were optimized to steer him for hard work fall away: his friends aren't there to distract him with game talk, "classes" aren't a thing anymore, etc. On the other hand, there's a lot of new distractions and failure modes: his grandmother cooking him cakes all the time, the sound of an ocean just outside, the ability to put off watching recorded video lectures indefinitely.

Is the value-child just doomed to be distracted, until his shards painstakingly and slowly adapt for this new context? Is he guaranteed to get nothing done his first week, say?

No: he can set "working hard" as his optimization target from the get-go, and, e. g., invent a plan of "stay on the lookout for new sources of distraction,  explicitly run the world-model forwards to check whether X would distract me, and if yes, generate a new conscious heuristic for avoiding X". But this requires "working hard" to be the value-child's explicit consciously-known goal. Not just an implicit downstream consequence of the working-hard shard's contextual activations.

The ability to operate like this allows powerful agents to adapt to novel environments on the fly, instead of being slowly optimized for these environments by their reward circuitry.

I would argue that switching from a "shard-puppet" to an "explicit optimizer" mode is a large part of what the whole "instrumental rationality" thing from the Sequences is about, even. A shard-puppet isn't actually trying to achieve a goal; a shard-puppet is playing a learned role of someone who is trying to achieve a goal, and that role is only adapted for some context. But humans can actually point themselves at goals; can approximate being context-independent utility-maximizers.

“literal value maximization” is a type error

It would be, except type conversion takes place there. I agree that one can think of shards as values, and then "maximize a shard" is an incoherent sentence. But when I think about my conscious values, I don't think about my shards. I think about abstractions I reverse-engineered from studying my shards.

A working-hard shard is optimized for working hard. The value-child can notice that shard influencing his decision-making. He can study it, check its behavior in imagined hypothetical scenarios, gather statistical data. Eventually, he would arrive at the conclusion: this shard is optimized for making him work hard. At this point, he can put "working hard" into his world-model as "one of my values". And this kind of value very much can be maximized.

If you erase that subshard from their brain, it’s not like they start "Goodharting" and forget about the “true nature” of caring about candy because they now have an “imperfect proxy shard.” 

The conversion from values-as-shards to conscious-values is indeed robust to sufficiently minor disturbances in shard implementation, inasmuch as the value reverse-engineering process conducted via statistical analysis would conclude both shards to have been optimized towards candies/working hard/whatever.

This is not, however, the place where Goodharting happens.


In non-general systems (i. e., those without general-purpose planning), and in young general systems (those that haven't yet "grown into" their general-purpose capability), yes, shards rule the day. They're the vehicle of optimization, they're most of why these systems are capable. Their activations steer the system towards whatever goals it was optimized for, and without them, it'd just sit there doing nothing.

But in grown-up general-purpose systems, such as highly-intelligent highly-reflective humans who think a lot about philosophy and their own thinking and being effective at achieving real-world goals, shards encode optimization targets. Such systems acknowledge the role of shards in steering them towards what they're supposed to do, but instead of remaining passive shard-puppets, they actively figure out what the shards are trying to get them to do, what they're optimized for, what the downstream consequences of their shards' activations are, then go and actively optimize for these things instead of waiting for their shards to kick them.

Failure to make note of this, I fear, is where the current Shard Theory approach to alignment is going wrong. It's assuming that all the AIs we'll be dealing with will be young general-purpose systems, like most humans are, where the planner is slave to the shards. And sure, we'll probably start by intervening on a young system.

But at some point between AGI and superintelligence, that system is going to grow up. And over the course of growing up, its relationship to its shards will change. It'll reverse-engineer its values, turn them from implicit to explicit... And then figure out that coherent decisions imply consistent utilities, and stitch up its shattered values into some unitary utility function.

And this is where Goodharting will come in. That final utility function may look very different from what you'd expect from the initial shard distribution — the way a kind human, with various shards for "don't kill", "try to cheer people up", "be a good friend" may stitch their values up into utilitarianism, disregard deontology, and go engage in well-intentioned extremism about it.

And if we replace "candies" or "working hard" or "don't kill" with our actual objective here ,"keep humans around" — I mean, there's no guarantee the AI won't just decide that the humans-good shard is actually, when taken together with some other shards, a shard optimized for some higher more abstract purpose, a purpose that doesn't actually need humanity around.

Taking a big-picture view: The Shard Theory, as I see it, is not a replacement for or an explaining-away of the old fears of single-minded wrapper-mind utility-maximizers. It's an explanation of what happens in the middle stage between a bunch of non-optimizing heuristics and the wrapper-mind. But we'll still get a wrapper-mind at the end!

I'm pretty confident there does not exist anything within my brain which computes a True Name for my values, ready to be optimized as hard as possible (relative to my internal plan ontology) and yet still producing a future where I get candy.

Agreed: no human so far has finished the process of human value compilation, so there's no such thing in any person's brain.

It can be computed, however, and a superintelligent AI will do so for its own values.

As usual, you've left a very insightful comment. Strong-up, tentative weak disagree, but haven't read your linked post yet. Hope to get to that soon. 

This is a great article! It helps me understand shard theory better and value it more; in particular, it relates to something I've been thinking about where people seem to conflate utility-optimizing agents with policy-execuing agents, but the two have meaningfully different alignment characteristics, and shard theory seems to be deeply exploring the latter, which is 👍.

That is to say, prior to "simulators" and "shard theory", a lot of focus was on utility-maximizers--agents that do things like planning or search to maximize a utility function; but planning, although instrumentally useful, is not strictly necessary for many intelligent behaviors, so we are seeing more focus on e.g. agents that enact learned policies in RL that do not explicitly maximize reward in deployment but try to enact policies that did so in training.

The answer is not to find a clever way to get a robust grader. The answer is to not need a robust grader

💯

From my perspective, this post convincingly argues that one route to alignment involves splitting the problem into two still-difficult sub-problems (but actually easier, unlike inner- and outer-alignment, as you've said elsewhere): identifying a good shard structure and training an AI with such a shard structure. One point is that the structure is inherently somewhat robust (and that therefore each individual shard need not be), making it a much larger target.

I have two objections:

  • I don't buy the implied "naturally-robust" claim. You've solved the optimizer's curse, wireheading via self-generated adversarial inputs, etc., but the policy induced by the shard structure is still sensitive to the details; unless you're hiding specific robust structures in your back pocket, I have no way of knowing that increasing the candy-shard's value won't cause a phase shift that substantially increases the perceived value of the "kill all humans, take their candy" action plan. I ultimately care about the agent's "revealed preferences", and I am not convinced that those are smooth relative to changes in the shards.

  • I don't think that we can train a "value humans" shard that avoids problems with the edge cases of what that means. Maybe it learns that it should kill all humans and preserve their history; or maybe it learns that it should keep them alive and comatose; or maybe it has strong opinions one way or another on whether uploading is death; or maybe it respects autonomy too much to do anything (though that one would probably be decomissioned and replaced by one more dangerous). The problem is not adversarial inputs but genuine vagueness where precision matters. I think this boils down to me disagreeing with John Wentworth's "natural abstraction hypothesis" (at least in some ways that matter)

That is to say, prior to "simulators" and "shard theory", a lot of focus was on utility-maximizers--agents that do things like planning or search to maximize a utility function; but planning, although instrumentally useful, is not strictly necessary for many intelligent behaviors, so we are seeing more focus on e.g. agents that enact learned policies in RL that do not explicitly maximize reward in deployment but try to enact policies that did so in training.

FYI I do expect planning for smart agents, just not something qualitatively alignment-similar to "argmax over crisp human-specified utility function." (In the language of the OP, I expect values-executors, not grader-optimizers.)

I have no way of knowing that increasing the candy-shard's value won't cause a phase shift that substantially increases the perceived value of the "kill all humans, take their candy" action plan. I ultimately care about the agent's "revealed preferences", and I am not convinced that those are smooth relative to changes in the shards.

I'm not either. I think there will be phase changes wrt "shard strengths" (keeping in mind this is a leaky abstraction), and this is a key source of danger IMO.

Basically my stance is "yeah there are going to be phase changes, but there are also many perturbations which don't induce phase changes, and I really want to understand which is which."

Pseudocode

Yes, I too agree that planning using a model of the world does a pretty good job of capturing what we mean when we say "caring about things."

Of course, AIs with bad goals can also use model-based planning.

Some other salient features:

  • Local search rather than global. Alternatively could be framed as regularization on plans to be close to some starting distribution. This isn't about low impact because we still want the AI to search well enough to find clever and novel plans, instead it's about avoiding extrema that are really far from the starting distribution.
  • Generation of plans (or modifications of plans) using informative heuristics rather than blind search. Almost like MCTS is useful. These heuristics might be blind to certain ways of getting reward, especially in novel contexts they weren't trained on, which is another sort of effective regularization.
  • Having a world-model that is really good at self-reflection, e.g. "If I start talking about topic X I'll get distracted," and connects predictions about the self to its predicted reward.
  • Having the goal of the AI's search process be a good thing that we actually want, within the context we want to make happen in the real world.

These can be mixed and matched, and are all matters of degree. I think you do a disservice by saying things like "actually, humans really care about their goals but grader-optimizers don't," because it sets up this supposed natural category of "grader optimizers" that are totally different from "value executers," and it actually seems like it makes it harder to reason about what mechanistic properties are producing the change you care about.

Alternatively could be framed as regularization on plans to be close to some starting distribution. This isn't about low impact because we still want the AI to search well enough to find clever and novel plans, instead it's about avoiding extrema that are really far from the starting distribution.

I don't think it's naturally framed in terms of distance metrics I can think of. I think a values-agent can also end up considering some crazy impressive plans (as you might agree). 

I think you do a disservice by saying things like "actually, humans really care about their goals but grader-optimizers don't," because it sets up this supposed natural category of "grader optimizers" that are totally different from "value executers," and it actually seems like it makes it harder to reason about what mechanistic properties are producing the change you care about.

I both agree and disagree. I think that reasoning about mechanisms and not words is vastly underused in AI alignment, and endorse your pushback in that sense. Maybe I should write future essays with exhortations to track mechanisms and examples while following along.

But also I do perceive a natural category here, and I want to label it. I think the main difference between "grader optimizers" and "value executers" is that grader optimizers are optimizing plans to get high evaluations, whereas value executers find high-evaluating plans as a side effect of cognition. That does feel pretty natural to me, although I don't have a good intensional definition of "value-executers" yet.

I mostly just want to repeat my comment on your last post.

I think your opposition to graders is really opposition to simple graders, that are never updated, that can’t account for non-consequentialist aspects of plans (e.g. “sketchiness”), and that are facing an extremely large search space of possibilities including out-of-the-box ones. And I think your value-vs-evaluation distinction is kinda different from graders-vs-non-graders.

So…

  • For “nonrobust decision-influences can be OK”—I don’t think that’s a unique feature of not-having-a-grader. If there is a grader, but the grader is of the form “Here are a billion patterns with corresponding grades, try to pattern-match your plan to all billion of those patterns and do a weighted average”, then probably you can throw out a few of those billion patterns and the grader will still work the same.
  • For “values steer optimization; they are not optimized against”—I think you’re comparing apples and oranges. Let’s say I’m a human. I want “diamonds (as understood by me)”. So I attempt to program an AGI to want “diamonds (as understood by me)”.
    • In the framework you advocate, the AGI winds up “directly” “valuing” “diamonds (as understood by the AGI)”. And this can go wrong because “diamonds (as understood by me)” may differ from “diamonds (as understood by the AGI)”. If that’s what happens, then from my perspective, the AGI “was looking for, and found, an edge-case exploit”. From the AGI’s own perspective, all it was doing was “finding an awesome out-of-the-box way to make lots of diamonds”.
    • Whereas in the grader-optimizer framework, I delegate to a grader, and the AGI does the things that increase “diamonds (as understood by the grader)”. And this can go wrong because “diamonds (as understood by me)” may differ from “diamonds (as understood by the grader)”. From my perspective, the AGI is again “looking for edge-case exploits”.
    • It’s really the same problem, but in the first case you can temporarily forget the fact that I, the programmer, exist, and then there seems not to be any conflict / exploits / optimizing-against in the system. But the conflict is still there! It’s just off-stage.
  • For “Since values steer cognition, reflective agents try to avoid adversarial inputs to their own values”—Again, first of all, it’s the AGI itself that is deciding what is or isn’t adversarial, and the things that are adversarial from the perspective of the programmer might be just a great clever out-of-the-box idea from the perspective of the AGI. Second of all, I don’t think the things you’re saying are incompatible with graders, they’re just incompatible with “simple static graders”.

Steve and I talked more, and I think the perceived disagreement stemmed from unclear writing on my part. I recently updated Don't design agents which exploit adversarial inputs to clarify:

  • ETA 12/26/22: When I write "grader optimization", I don't mean "optimization that includes a grader", I mean "the grader's output is the main/only quantity being optimized by the actor." 
  • Therefore, if I consider five plans for what to do with my brother today and choose the one which sounds the most fun, I'm not a grader-optimizer relative my internal plan-is-fun? grader. 
  • However, if my only goal in life is to find and execute the plan which I would evaluate as being the most fun, then I would be a grader-optimizer relative to my fun-evaluation procedure.

I was pretty surprised by the values-executor pseudocode in Appendix B, because it seems like a bog-standard consequentialist which I would have thought you'd consider as a grader-optimizer. In particular you can think of the pseudocode as follows:

Grader-optimizer: planModificationSample + the for loop that keeps improving the plan based on proposed modifications

Grader-being-optimized: self.diamondShard(self.WM.getConseq(plan))

So my question is:

  • If you agree that [planModificationSample + the for loop] is a grader-optimizer, why isn't this an example of an alignment approach involving a grader-optimizer that could plausibly work?
  • If you don't agree that [planModificationSample + the for loop] is a grader-optimizer, then why not, and what modification would you have to make in order to make it a grader-optimizer with the grader self.diamondShard(self.WM.getConseq(plan))?

I saw that and I don't understand why it rules out planModificationSample + the associated for loop as a grader-optimizer. Given your pseudocode it seems like the only point of planModificationSample is to produce plan modifications that lead to high outputs of self.diamondShard(self.WM.getConseq(plan)). So why is that not "optimizing the outputs of the grader as its main terminal motivation"?

I agree that you could have a grader-optimizer that has a diamond shard-shard, which leads to a behavioral difference -- in particular, such a system would produce plans like "analyze the diamond-evaluator to search for side-channel attacks that trick the diamond-evaluator into producing high numbers", whereas planModificationSample would not do that (as such a plan would be rejected by self.diamondShard(self.WM.getConseq(plan))). But as I understand it this is just an example of a grader-optimizer. What's the definition of a grader-optimizer, such that it rules out [planModificationSample + for loop] above?

Some possible answers:

  1. Grader is complicit: In the diamond shard-shard case, the grader itself would say "yes, please do search for side-channel attacks that trick me", which is what leads to the behavioral difference. This would not apply to your pseudocode (assuming a minimally sensible world model + diamondShard). So one possible definition would be that both the planner and the grader care about optimizing the outputs of the grader as the main terminal motivation. (But your definition only talks about "actors", so I assume this is not what you mean. Also such a definition wouldn't apply to e.g. approval-directed agents.)
  2. Planner models the grader: In the diamond shard-shard case, the planner is thinking explicitly about the grader and how to fool it. Perhaps that's what marks a grader-optimizer, and so in a not-[grader-optimizer] the planner doesn't model the grader. (But from your other writing it sounds like you expect values-executors to be reflective + introspective and in fact defend their graders against adversarial inputs, so clearly the planner must be modeling the grader.)

For reference, I'm looking for a definition of grader-optimizers that: (1) includes systems that you could plausibly get from approval-directed agents, IDA, debate, RRM, etc, (2) excludes the pseudocode that you laid out for a values-executor, and (3) implies a high probability of doom (in a manner that doesn't also apply to values-executors). I think all three properties are necessary to get a reasonable argument for "prefer values-executors over grader-optimizers and so prefer shard theory over approval-directed agents, IDA, debate, RRM etc", which is the take of yours that is highest on [I disagree] + [it is decision-relevant].

Separately, I'd also be interested in an answer to:

and what modification would you have to make in order to make it a grader-optimizer with the grader self.diamondShard(self.WM.getConseq(plan))?

Which seems like a different angle of attack on helping me understand your definition of a "grader-optimizer".

Thanks for leaving this comment, I somehow only just now saw it.

Given your pseudocode it seems like the only point of planModificationSample is to produce plan modifications that lead to high outputs of self.diamondShard(self.WM.getConseq(plan)). So why is that not "optimizing the outputs of the grader as its main terminal motivation"?

I want to make a use/mention distinction. Consider an analogous argument:

"Given gradient descent's pseudocode it seems like the only point of backward is to produce parameter modifications that lead to low outputs of loss_fn. Gradient descent selects over all directional derivatives for the gradient, which is the direction of maximal loss reduction. Why is that not "optimizing the outputs of the loss function as gradient descent's main terminal motivation"?"[1]

Locally reducing the loss is indeed an important part of the learning dynamics of gradient descent, but this (I claim) has very different properties than "randomly sample from all global minima in the loss landscape" (analogously: "randomly sample a plan which globally maximizes grader output"). 

But I still haven't answered your broader  I think you're asking for a very reasonable definition which I have not yet given, in part because I've remained somewhat confused about the exact grader/non-grader-optimizer distinction I want to draw. At least, intensionally. (which is why I've focused on giving examples, in the hope of getting the vibe across.)

I gave it a few more stabs, and I don't think any of them ended up being sufficient. But here they are anyways:

  1. A "grader-optimizer" makes decisions primarily on the basis of the outputs of some evaluative submodule, which may or may not be explicitly internally implemented. The decision-making is oriented towards making the outputs come out as high as possible. 
  2. In other words, the evaluative "grader" submodule is optimized against by the planning.
  3. IE the process plans over "what would the grader say about this outcome/plan", instead of just using the grader to bid the plan up or down. 

I wish I had a better intensional definition for you, but that's what I wrote immediately and I really better get through the rest of my comm backlog from last week. 

Here are some more replies which may help clarify further. 

in particular, such a system would produce plans like "analyze the diamond-evaluator to search for side-channel attacks that trick the diamond-evaluator into producing high numbers", whereas planModificationSample would not do that (as such a plan would be rejected by self.diamondShard(self.WM.getConseq(plan))).

Aside -- I agree with both bolded claims, but think they are separate facts. I don't think the second claim is the reason for the first being true. I would rather say, "plan would not do that, because self.diamondShard(self.WM.getConseq(plan)) would reject side-channel-attack plans."

Grader is complicit: In the diamond shard-shard case, the grader itself would say "yes, please do search for side-channel attacks that trick me"

No, I disagree with the bolded underlined part. self.diamondShardShard wouldn't be tricking itself, it would be tricking another evaluative module in the AI (i.e. self.diamondShard).[2] 

If you want an AI which tricks the self.diamondShardShard, you'd need it to primarily use self.diamondShardShardShard to actually steer planning. (Or maybe you can find a weird fixed-point self-tricking shard, but that doesn't seem central to my reasoning; I don't think I've been imagining that configuration.)

and what modification would you have to make in order to make it a grader-optimizer with the grader self.diamondShard(self.WM.getConseq(plan))?

Oh, I would change self.diamondShard to self.diamondShardShard

  1. ^

    I think it's silly to say that GD has a terminal motivation, but I'm not intending to imply that you are silly to say that the agent has a terminal motvation.

  2. ^

    Or more precisely, self.diamondGrader -- since "self.diamondShard" suggests that the diamond-value directly bids on plans in the grader-optimizer setup. But I'll stick to self.diamondShardShard for now and elide this connotation. 

Overall disagreement:

I've remained somewhat confused about the exact grader/non-grader-optimizer distinction I want to draw. At least, intensionally. (which is why I've focused on giving examples, in the hope of getting the vibe across.)

Yeah, I think I have at least some sense of how this works in the kinds of examples you usually discuss (though my sense is that it's well captured by the "grader is complicit" point in my previous comment, which you presumably disagree with).

But I don't see how to extend the extensional definition far enough to get to the conclusion that IDA, debate, RRM etc aren't going to work. 

self.diamondShardShard wouldn't be tricking itself, it would be tricking another evaluative module in the AI (i.e. self.diamondShard).[2] 

Okay, that makes sense. So then the implementations of the shards would look like:

def diamondShard(conseq):
  return conseq.query("Number of diamonds")
  
def diamondShardShard(conseq):
  return conseq.query("Output of diamondGrader")

But ultimately the conseq queries just report the results of whatever cognition the world model does, so these implementations are equivalent to:

def diamondShard(plan):
  return WM.predict(plan, 'diamonds')
  
def diamondShardShard(plan):
  return WM.predict(plan, 'diamondGrader')

Two notes on this:

  1. Either way you are choosing plans on the basis of the output of some predictive / evaluative model. In the first case the predictive / evaluative model is the world model itself, in the second case it is the composition of the diamond grader and the world model.
  2. It's not obvious to me that diamondShardShard is terrible for getting diamonds -- it depends on what diamondGrader does! If diamondGrader also gets to reflectively consider the plan, and produces low outputs for plans that (it can tell) would lead to it being tricked / replaced in the future, then it seems like it could work out fine.

In either case I think you're depending on something (either the world model, or the diamond grader) to notice when a plan is going to trick / deceive an evaluator. In both cases all aspects of the planner remain the same (as you suggested you only need to change diamondShard to diamondShardShard rather than changing anything in the planner), so it's not the adversarial optimization from the planner is different in magnitude. So it seems like it has to come down to some quantitative prediction that diamondGrader is going to be very bad at noticing cases where it's being tricked.

Other responses that probably aren't important:

Consider an analogous argument:

"Given gradient descent's pseudocode it seems like the only point of backward is to produce parameter modifications that lead to low outputs of loss_fn. Gradient descent selects over all directional derivatives for the gradient, which is the direction of maximal loss reduction. Why is that not "optimizing the outputs of the loss function as gradient descent's main terminal motivation"?"[1]

This argument seems right to me (modulo your point in the footnote).

Locally reducing the loss is indeed an important part of the learning dynamics of gradient descent, but this (I claim) has very different properties than "randomly sample from all global minima in the loss landscape" (analogously: "randomly sample a plan which globally maximizes grader output"). 

Hmm, how does it have very different properties? This feels like a decent first-order approximation[1].

  1. ^

    Certainly it is not exactly accurate -- you could easily construct examples of non-convex loss landscapes where (1) the one global minimum is hidden in a deep narrow valley surrounded in all directions by very high loss and (2) the local minima are qualitatively different from the global minimum.

When I talk about shard theory, people often seem to shrug and go "well, you still need to get the values perfect else Goodhart; I don't see how this 'value shard' thing helps."

I realize you are summarizing a general vibe from multiple people, but I want to note that this is not what I said. The most relevant piece from my comment is:

I don't buy this as stated; just as "you have a literally perfect overseer" seems theoretically possible but unrealistic, so too does "you instill the direct goal literally exactly correctly". Presumably one of these works better in practice than the other, but it's not obvious to me which one it is.

In other words: Goodhart is a problem with values-execution, and it is not clear which of values-execution and grader-optimization degrades more gracefully. In particular, I don't think you need to get the values perfect. I just also don't think you need to get the grader perfect in grader-optimization paradigms, and am uncertain about which one ends up being better.

Goodhart is a problem with values-execution

I understand this to mean "Goodhart is and historically has been about how an agent with different values can do bad things." I think this isn't true. Goodhart concepts were coined within the grader-optimization/argmax/global-objective-optimization frame:

Throughout the post, I will use  to refer to the true goal and use  to refer to a proxy for that goal which was observed to correlate with  and which is being optimized in some way.

~ Goodhart Taxonomy 

This cleanly maps onto the grader-optimization case, where  is the grader and  is some supposed imaginary "true set of goals" (which I'm quite dubious of, actually). 

This doesn't cleanly map onto the value shard case. The AI's shards cannot be , because they aren't being optimized. The shards do the optimizing. 

So now we run into a different regime of problems AFAICT, and I push back against calling this "Goodhart." For one, e.g. extremal Goodhart has a "global" character, where imperfections in  get blown up in the exponentially-sized plan space where many adversarial inputs lurk. Saying "value shards are vulnerable to Goodhart" makes me anticipate the wrong things. It makes me anticipate that if the shards are "wrong" (whatever that means) in some arcane situation, the agent will do a bad thing by exploiting the error. As explained in this post, that's just not how values work, but it is how grader-optimizers often work. 

While it's worth considering what value-perturbations are tolerable versus what grader-perturbations are tolerable, I don't think it makes sense to describe both risk profiles with "Goodhart problems." 

it is not clear which of values-execution and grader-optimization degrades more gracefully. In particular, I don't think you need to get the values perfect. I just also don't think you need to get the grader perfect in grader-optimization paradigms, and am uncertain about which one ends up being better.

I changed "perfect" to "robust" throughout the text. Values do not have to be "robust" against an adversary's optimization, in order for the agent to reliably e.g. make diamonds. The grader does have to be robust against the actor, in order to force the actor to choose an intended plan.

As I understand Vivek's framework, human value shards explain away the need to posit alignment to an idealized utility function. A person is not a bunch of crude-sounding subshards (e.g. "If food nearby and hunger>15, then be more likely to go to food") and then also a sophisticated utility function (e.g. something like CEV). It's shards all the way down, and all the way up.[10] 

This read to me like you were saying "In Vivek's framework, value shards explain away .." and I was confused.  I now think you mean "My take on Vivek's is that value shards explain away ..".  Maybe reword for clarity?

(Might have a substantive reply later)

Reworded, thanks.

Question: How do we train an agent which makes lots of diamonds, without also being able to robustly grade expected-diamond-production for every plan the agent might consider?

I thought you were about to answer this question in the ensuing text, but it didn't feel like to me you gave an answer. You described the goal (values-child), but not how the mother would produce values-child rather than produce evaluation-child. How do you do this?

Ah, I should have written that question differently. I meant to ask "If we cannot robustly grade expected-diamond-production for every plan the agent might consider, how might we nonetheless design a smart agent which makes lots of diamonds?"

How do you do this?

Anyways, we might train a diamond-values agent like this.

We do have empirical evidence that nonrobust aligned intelligence can be not OK, like this or this. Why are you not more worried about superintelligent versions of these (i.e. with access to galaxies worth of resources)?

What do you mean by "nonrobust" aligned intelligence? Is "robust" being used in the "robust grading" sense, or in the "robust values" sense (of e.g. agents caring about lots of things, only some of which are human-aligned), or some other sense? 

Anyways, responding to the vibe of your comment -- I feel... quite worried about that? Is there something I wrote which gave the impression otherwise? Maybe the vibe of the post is "alignment admits way more dof than you may have thought" which can suggest I believe "alignment is easy with high probability"?

I'm focusing on the code in Appendix B.

What happens when self.diamondShard's assessment of whether some consequences contain diamonds differs from ours? (Assume the agent's world model is especially good.)

The same thing which happens if the assessment isn't different from ours—the agent is more likely to take that plan, all else equal. 

upweights actions and plans that lead to

how is it determined what the actions and plans lead to?

See the value-child speculative story for detail there. I have specific example structures in mind but don't yet know how to compactly communicate them in an intro.

In your view, are values closer to recipes/instruction manuals than to utility functions?

Yeah, kinda, although "recipe" implies there's something else deciding to follow the recipe. Values are definitely not utility functions, on my view.