I renamed the phenomenon to “runaway optimiser”. I hope this label illustrates the inappropriately unbounded and single-minded nature of the failure modes we observed. How does that sound to you, does that capture the essence of the phenomena described in the post?
Roland Pihlakas
Karma: 113
Thank you for pointing that out! I agree, there are couple of nuances. Our perspective can be treated as a generalisation of the original utility monster scenario. Although I consider it to be not first such generalisation—think of the examples in Bostrom’s book.
1) In our case, the dilemma is not “agent versus others”, but instead “one objective versus other objectives”. One objective seems to get more internal/subjective utility from consumption than another objective. Thus the agent focuses on a single objective only.
2) Consideration of homeostatic objectives introduces a new aspect to the utility monster problem—the behaviour of the original utility monster looks unaligned to begin with, not just dominating. It is unnatural for a being to benefit from indefinite consumption. It looks like the original utility monster has an eating disorder! It enjoys eating apples so much that it does not care about the consequences to the future (“other”) self. That means, even the utility monster may actually suffer from “too much consumption”. But it does not recognise it and therefore it consumes indefinitely. Alternatively, just as a paperclip maximiser does not produce the paper clips for themselves—if the utility monster is an agent, then somebody else suffers from homeostasis violations while the agent is being “helpful” in an unaligned and naive way. Technically, this can be seen as a variation of the multi-objective problem—active avoidance of overconsumption could be treated as an “other” objective, while consumption is the dominating and inaccurately linear “primary” objective with a non-diminishing utility.
In conclusion, our perspective is a generalisation: whether the first objective is for agent’s own benefit and the other objective for the benefit of others, is left unspecified in our case. Likewise, violating homeostasis can be a scenario where an unaligned agent gets a lot of internal/subjective “utility” from making you excessively happy or from overfeeding you, while you are the one who suffers from overwhelm or overconsumption.
Hope that clears things up? I am also curious, would you like to share, what might be an alternative short name for the phenomena desribed in this post?
Notable runaway-optimiser-like LLM failure modes on Biologically and Economically aligned AI safety benchmarks for LLMs with simplified observation format
I agree, sounds plausible that this could happen. Likewise as we humans may build a strongly optimising agent because we are lazy and want to use simpler forms of maths. The tiling agents problem is definitely important.
That being said, agents properly understanding and modelling homeostasis is among the required properties (thus essential). It is not meant to be sufficient one. There may be no single sufficient property that solves everything, therefore there is no competition between different required properties. Required properties are conjunctive, they are all needed. My intuition is that homeostasis is one such property. If we neglect homeostasis then we are likely in trouble regardless of advances in other properties.
If we leave aside the question of sloppiness in creating sub-agents, I disagree with the zero cost assumption in the problem you described. I also disagree that it would be an expected and acceptable situation to have powerful agents having a singular objective. As the title of this blog post hints—we need a plurality of objectives.Having a sub-agent does not change this. Whatever the sub-agent does, will be the responsibility or liability of the main agent who will be held accountable. Legally, one should not produce random sub-agents running amok.
In addition to homeostasis, a properly constructed sub-agent should understand the principle of diminishing returns in instrumental objectives. This topic I do mention towards the end of this blog post. We can consider wall-building as an instrumental objective. But instrumental objectives are not singular and in isolation either, there are also a plurality of these. Thus, spending excessive resources on a single instrumental objective is not economically cost-efficient. Therefore, it makes sense to stop the wall building and switch over to some other objective at some point. Or at least to continue improving the walls only when other objectives have been sufficiently attended to as well—thus providing balancing across objectives.
Secondly, a proper sub-agent should also keep in mind the homeostatic objectives of the main agent. If some homeostatic objective from among the plurality of homeostatic objectives would get harmed as a side effect of the excessive wall-building, then that needs to be taken into consideration. Depending on the situation, the main agent might potentially care about these side effects before it launches the sub-agent.
Thirdly, following the principles of homeostasis does not necessarily mean laziness and sloppiness in everything. Instead, homeostasis primarily notes that unbounded maximisation of a homeostatic objective is incompatible and harmful even for the very objective that was maximised for. In addition to potentially having side effects to the plurality of other objectives. So homeostasis is primarily about minding the target value as opposed to maximisation of the actual value. An additional relevant principle is minding the plurality of objectives.
Finally, when an agent has a task to produce 100 paper clips then that does not mean that the number of paper clips needs to stay at 100 after the task has been completed. Perhaps it is entirely expected that these 100 paper clips will be carried away by authorised parties. Walls help against theft and environmental degradation of produced paper clips, but we do not exactly need the walls to keep the paperclip number at 100 at all times—there is some deeper need or transaction behind the requested paper clips.
In order to avoid confusion, pointing also out that there are two types of balancing involved in these topics:
1. Balancing of an homeostatic objective—keeping the actual value of a single homeostatic objective near the target value—not too low, not too high.
2. Balancing across objectives—as a form of considering the utilities of multiple objectives equally. That means meeting them in such a manner that the homeostatic objectives have for example least-squares deviations, while unbounded objectives have approximately same utility value after the utility functions with diminishing returns have been applied to each actual value.
I am curious, how does this land with you and does this respond to your question?
Why modelling multi-objective homeostasis is essential for AI alignment (and how it helps with AI safety as well)
Thank you for your question!
I agree that the simulations need to have sufficient complexity. Indeed, that was one of main motivations I became interested in creating multi-objective benchmarks in the past. Various AI safety toy problems seemed to me so much simplified that they lacked essential objectives and other decisive nuances. This motivation is still very much one of my main driving motivations.
That being said, complexity has also downsides:
1) The complexity introduces confounding factors. When a model fails such a benchmark, it is not clear whether it was because it did not have required perceptual capabilities (so it is a capabilities problem), or it is using a model/framework that is unsuitable for alignment (so it is an alignment problem).
2) Running the simulations will be more time consuming and it would make the research elitist in the sense that various people would not be able to afford it.My plan is to try to start with preference towards simple, but not simpler than necessary. And then gradually make it more complex. That means trying to use the gridworlds and introducing as many symbols as is needed to represent the important objectives, objects, other concepts and phenomena, and their interactions.
I believe symbolic approaches should not be entirely dismissed. As an illustrative metaphor, I am thinking of books—they contains symbols, yet we consider them as a cornerstone of our civilization. Similarly to the current dilemma with benchmarks, we may then worry whether books are too simple and symbol based—or perhaps one should prefer watching movies instead, since they represent reality in more detail. But would that claim be necessarily true? It does not seem so obvious after all.
In case more complexity is needed, there are currently at least five ideas:
1) Adding more feature layers to the gridworld. I did not mention it before, but the observation format already supports multiple concurrent observable layers on top of each other. One of the layers could be for example facial expressions, or any other observable or partially unobservable metrics relevant to objects they accompany.
2) Adding textual messages between agents as a side panel to the gridworlds.
3) Making the environment bigger, so there are more objects and more phenomena.
4) Making the environment bigger and making also the objects bigger so that they cover multiple cells in the grid. Thus the objects will become composite, consisting of sub-parts with their own dynamics.
5) Using some other framework, for example Sims.Curious, how do these thoughts and considerations land with you?
Building AI safety benchmark environments on themes of universal human values
I think your own message is also too extreme to be rational. So it seems to me that you are fighting fire with a fire. Yes, Remmelt has some extreme expressions, but you definitely have extreme expressions here too, while having even weaker arguments.
Could we find a golden middle road, a common ground, please? With more reflective thinking and with less focus on right and wrong?
I agree that Remmelt can improve the message. And I believe he will do that.
I may not agree that we are going to die with 99% probability. At the same time I find that his current directions are definitely worthwhile of exploring.
I also definitely respect Paul. But mentioning his name here is mostly irrelevant for my reasoning or for taking your arguments seriously, simply because I usually do not take authorities too seriously before I understand their reasoning in a particular question. And understanding a person’s reasoning may occasionally mean that I disagree in particular points as well. In my experience, even the most respectful people are still people, which means they often think in messy ways and they are good just on average, not per instance of a thought line (which may mean they are poor thinkers 99% of the time, while having really valuable thoughts 1% of the time). I do not know the distribution for Paul, but definitely I would not be disappointed if he makes mistakes sometimes.I think this part of Remmelt’s response sums it up nicely: “When accusing someone of crankery (which is a big deal) it is important not to fall into making vague hand-wavey statements yourself. You are making vague hand-wavey (and also inaccurate) statements above. Insinuating that something is “science-babble” doesn’t do anything. Calling an essay formatted as shorter lines a “poem” doesn’t do anything.”
In my interpretation, black-and-white thinking is not “crankery”. It is a normal and essential step in the development of cognition about a particular problem. Unfortunately. There is research about that in the field of developmental and cognitive psychology. Hopefully that applies to your own black-and-white thinking as well. Note that, unfortunately this development is topic specific, not universal.
In contrast, “crankery” is too strong word for describing black-and-white thinking because it is a very judgemental word, a complete dismissal, and essentially an expression of unwillingness to understand, an insult, not just a disagreement about a degree of the claims. Is labelling someone’s thoughts as “a crankery” also a form of crankery of its own then? Paradoxical isn’t it?
The following is meant as a question to find out, not a statement of belief.
Nobody seems to have mentioned the possibility that initially they did not intend to fire Sam, but just to warn him or to give him a choice to restrain himself. Yet possibly he himself escalated it to firing or chose firing instead of complying with the restraint. He might have done that just in order to have all the consequences that have now taken place, giving him more power.
For example, people in power positions may escalate disagreements, because that is a territory they are more experienced with as compared to their opponents.
The paper is now published with open access here:
https://link.springer.com/article/10.1007/s10458-022-09586-2
Sets of objectives for a multi-objective RL agent to optimize
I propose blacklists are less useful if they are about proxy measures, and much more useful if they are about ultimate objectives. Some of the ultimate objectives can also be represented in the form of blacklists. For example, listing many ways to kill a person is less useful. But saying that death or violence is to be avoided, is more useful.
I imagine that the objectives which fulfill the human needs for Power (control over AI), Self-Direction (autonomy, freedom from too much influence from AI), and maybe others, would be partially also working in ensuring that the AI does not start moving towards wireheading. Wireheading would surely be in contradiction to these objectives.
If we consider wireheading as a process, not a black and white event, then there are steps along the way. These steps could be potentially detected or even foreseen before the process finishes in a new equilibrium.
A question. Is it relevant for your current problem formulation that you also want to ensure that authorised people still have reasonable access to the diamond? In other words, is it important here that the system still needs to yield to actions or input from certain humans, be interruptible and corrigible? Or, in ML terms, does it have to avoid both false negatives and false positives when detecting or avoiding intrusion scenarios?
I imagine that an algorithmically more trivial way to make the system both “honest” and “secured” is to make it so heavily secured that almost certainly nobody can access the diamond.
Until the Modem website is down, you can access our workshop paper here: https://drive.google.com/file/d/1qufjPkpsIbHiQ0rGmHCnPymGUKD7prah/view?usp=sharing
You can apply the nonlinear transformation either to the rewards or to the Q values. The aggregation can occur only after transformation. When transformation is applied to Q values then the aggregation takes place quite late in the process—as Ben said, during action selection.
Both the approach of transforming the rewards and the approach of transforming the Q values are valid, but have different philosophical interpretations and also have different experimental outcomes to the agent behaviour. I think both approaches need more research.
For example, I would say that transforming the rewards instead of Q values is more risk-averse as well as “fair” towards individual timesteps, since it does not average out the negative outcomes across time before exponentiating them. But it also results in slower learning by the agent.Finally there is a third approach which uses lexicographical ordering between objectives or sets of objectives. Vamplew has done work on this direction. This approach is truly multi-objective in the sense that there is no aggregation at all. Instead the vectors must be compared during RL action selection without aggregation. The downside is that it is unwieldy to have many objectives (or sets of objectives) lexicographically ordered.
I imagine that the lexicographical approach and our continuous nonlinear transformation approaches are complementary. There could be for example two main sets of objectives: one set for alignment objectives, the other set for performance objectives. Inside a set there would be nonlinear transformation and then aggregation applied, but between the sets there would be lexicographical ordering applied. In other words there would be a hierarchy of objectives. By having only two sets in lexicographical ordering the lexicographical ordering does not become unwieldy.
This approach would be a bit analogous to the approach used by constraint programming, though more flexible. The safety objectives would act as a constraint against performance objectives. An approach that is almost in absurd manner missing from classical naive RL, but which is very essential, widely known, and technically developed in practical applications, that is, in constraint programming! In the hybrid approach proposed in the above paragraph the difference from classical constraint programming would be that among the safety objectives there would still be flexibility and ability to trade (in a risk-averse way).
Finally, when we say “multi-objective” then it does not just refer to the technical details of the computation. It also stresses the importance of acknowledging the need for researching and making more explicit the inherent presence and even structure of multiple objectives inside any abstract top objective. To encode knowledge in a way that constrains incorrect solutions but not correct solutions. As well as acknowledging the potential existence of even more complex, nonlinear interactions between these multiple objectives. We did not focus on nonlinear interactions between the objectives yet, but these interactions are possibly relevant in the future.
I totally agree that in a reasonable agent the objectives or target values / set-points do change, as it is also exemplified by biological systems.
Until the Modem website is down, you can access our workshop paper here: https://drive.google.com/file/d/1qufjPkpsIbHiQ0rGmHCnPymGUKD7prah/view?usp=sharing
A brief review of the reasons multi-objective RL could be important in AI Safety Research
Yes, maybe the the minimum cost is 3 even without floor or ceiling? But the question is then how to find concrete solutions that can be proven using realistic efforts. I interpret the challenge as request for submission of concrete solutions, not just theoretical ones. Anyway, my finding is below, maybe it can be improved further. And could there be any way to emulate floor or ceiling using the functions permitted in the initial problem formulation?
By the way, for me the >! works reliably when entered right in the beginning of the message. After a newline it does not work reliably.ceil(3!! * sqrt(sqrt(5! / 2 + 2)))
If you would allow ceiling function then I could give you a solution with score 60 for the Puzzle 1. Ceiling or floor functions are cool because they add even more branches to the search, and enable involving irrational number computations too. :P Though you might want to restrict the number of ceiling or floor functions permitted per solution.
By the way, please share a hint about how do you enter spoilers here?
Thank you for asking! I am encouraged to hear you find it important :) It is under Links section. Code, system prompts, output data files, plots, and a more detailed report can be found here: https://github.com/levitation-opensource/bioblue
Please let me know if you have any further questions! The GitHub readme document and PDF report contain a lot of information and maybe the structure could be improved in the future.
The Python code files for the four experiments are runnable independently from each other and are relatively short, about 250 − 300 lines each. To see the nuances of the results you might want to take a closer look at the output data files with your own eye.
This enables you to see that the models fail at different points in time, but the sequence of actions after failure point is usually typical. In the coming days, I will create one more output folder with annotated log files so the failure modes can be found more easily.