1)Which are the implicit assumptions, within MIRI’s research agenda, of things that “currently we have absolutely no idea of how to do that, but we are taking this assumption for the time being, and hoping that in the future either a more practical version of this idea will be feasible, or that this version will be a guiding star for practical implementations”?
I mean things like
UDT assumes it’s ok for an agent to have a policy ranging over all possible environments and environment histories
The notion of agent used by MIRI assumes to some extent that agents are functions, and that if you want to draw a line around the reference class of an agent, you draw it around all other entities executing that function.
The list of problems in which the MIRI papers need infinite computability is: X, Y, Z etc…
(something else)
And so on
2) How do these assumptions diverge from how FLI, FHI, or non-MIRI people publishing on the AGI 2014 book conceive of AGI research?
3) Optional: Justify the differences in 2 and why MIRI is taking the path it is taking.
1) The things we have no idea how to do aren’t the implicit assumptions in the technical agenda, they’re the explicit subject headings: decision theory, logical uncertainty, Vingean reflection, corrigibility, etc :-)
We’ve tried to make it very clear in various papers that we’re dealing with very limited toy models that capture only a small part of the problem (see, e.g., basically all of section 6 in the corrigibility paper).
Right now, we basically have a bunch of big gaps in our knowledge, and we’re trying to make mathematical models that capture at least part of the actual problem—simplifying assumptions are the norm, not the exception. All I can easily say that common simplifying assumptions include: you have lots of computing power, there is lots of time between actions, you know the action set, you’re trying to maximize a given utility function, etc. Assumptions tend to be listed in the paper where the model is described.
2) The FLI folks aren’t doing any research; rather, they’re administering a grant program. Most FHI folks are focused more on high-level strategic questions (What might the path to AI look like? What methods might be used to mitigate xrisk? etc.) rather than object-level AI alignment research. And remember that they look at a bunch of other X-risks as well, and that they’re also thinking about policy interventions and so on. Thus, the comparison can’t easily be made. (Eric Drexler’s been doing some thinking about the object-level FAI questions recently, but I’ll let his latest tech report fill you in on the details there. Stuart Armstrong is doing AI alignment work in the same vein as ours. Owain Evans might also be doing object-level AI alignment work, but he’s new there, and I haven’t spoken to him recently enough to know.)
Insofar as FHI folks would say we’re making assumptions, I doubt they’d be pointing to assumptions like “UDT knows the policy set” or “assume we have lots of computing power” (which are obviously simplifying assumptions on toy models), but rather assumptions like “doing research on logical uncertainty now will actually improve our odds of having a working theory of logical uncertainty before it’s needed.”
(3) I think most of the FHI folks & FLI folks would agree that it’s important to have someone hacking away at the technical problems, but just to make the arguments more explicit, I think that there are a number of problems that it’s hard to even see unless you have your “try to solve FAI” goggles on. Consider: people have been working on some of these problems for decades (logical uncertainty) or even centuries (decision theory) without solving the AI-alignment-relevant parts.
We’re still very much trying to work out the initial theory of highly reliable advanced agents. This involves taking various vague philosophical problems (“what even is logical uncertainty?”) and turning them into concrete mathematical models (akin to the concrete model of probability theory attained by Kolmogorov & co).
We’re still in the preformal stage, and if we can get this theory to the formal stage, I expect we may be able to get a lot more eyes on the problem, because the ever-crawling feelers of academia seem to be much better at exploring formalized problems than they are at formalizing preformal problems.
Then of course there’s the heuristic of “it’s fine to shout ‘model uncertainty!’ and hover on the sidelines, but it wasn’t the armchair philosophers who did away with the epicycles, it was Kepler, who was up to his elbows in epicycle data.” One of the big ways that you identify the things that need working on is by trying to solve the problem yourself. By asking how to actually build an aligned superintelligence, MIRI has generated a whole host of open technical problems, and I predict that that host will be a very valuable asset now that more and more people are turning their gaze towards AI alignment.
1)Which are the implicit assumptions, within MIRI’s research agenda, of things that “currently we have absolutely no idea of how to do that, but we are taking this assumption for the time being, and hoping that in the future either a more practical version of this idea will be feasible, or that this version will be a guiding star for practical implementations”?
I mean things like
UDT assumes it’s ok for an agent to have a policy ranging over all possible environments and environment histories
The notion of agent used by MIRI assumes to some extent that agents are functions, and that if you want to draw a line around the reference class of an agent, you draw it around all other entities executing that function.
The list of problems in which the MIRI papers need infinite computability is: X, Y, Z etc…
(something else)
And so on
2) How do these assumptions diverge from how FLI, FHI, or non-MIRI people publishing on the AGI 2014 book conceive of AGI research?
3) Optional: Justify the differences in 2 and why MIRI is taking the path it is taking.
1) The things we have no idea how to do aren’t the implicit assumptions in the technical agenda, they’re the explicit subject headings: decision theory, logical uncertainty, Vingean reflection, corrigibility, etc :-)
We’ve tried to make it very clear in various papers that we’re dealing with very limited toy models that capture only a small part of the problem (see, e.g., basically all of section 6 in the corrigibility paper).
Right now, we basically have a bunch of big gaps in our knowledge, and we’re trying to make mathematical models that capture at least part of the actual problem—simplifying assumptions are the norm, not the exception. All I can easily say that common simplifying assumptions include: you have lots of computing power, there is lots of time between actions, you know the action set, you’re trying to maximize a given utility function, etc. Assumptions tend to be listed in the paper where the model is described.
2) The FLI folks aren’t doing any research; rather, they’re administering a grant program. Most FHI folks are focused more on high-level strategic questions (What might the path to AI look like? What methods might be used to mitigate xrisk? etc.) rather than object-level AI alignment research. And remember that they look at a bunch of other X-risks as well, and that they’re also thinking about policy interventions and so on. Thus, the comparison can’t easily be made. (Eric Drexler’s been doing some thinking about the object-level FAI questions recently, but I’ll let his latest tech report fill you in on the details there. Stuart Armstrong is doing AI alignment work in the same vein as ours. Owain Evans might also be doing object-level AI alignment work, but he’s new there, and I haven’t spoken to him recently enough to know.)
Insofar as FHI folks would say we’re making assumptions, I doubt they’d be pointing to assumptions like “UDT knows the policy set” or “assume we have lots of computing power” (which are obviously simplifying assumptions on toy models), but rather assumptions like “doing research on logical uncertainty now will actually improve our odds of having a working theory of logical uncertainty before it’s needed.”
(3) I think most of the FHI folks & FLI folks would agree that it’s important to have someone hacking away at the technical problems, but just to make the arguments more explicit, I think that there are a number of problems that it’s hard to even see unless you have your “try to solve FAI” goggles on. Consider: people have been working on some of these problems for decades (logical uncertainty) or even centuries (decision theory) without solving the AI-alignment-relevant parts.
We’re still very much trying to work out the initial theory of highly reliable advanced agents. This involves taking various vague philosophical problems (“what even is logical uncertainty?”) and turning them into concrete mathematical models (akin to the concrete model of probability theory attained by Kolmogorov & co).
We’re still in the preformal stage, and if we can get this theory to the formal stage, I expect we may be able to get a lot more eyes on the problem, because the ever-crawling feelers of academia seem to be much better at exploring formalized problems than they are at formalizing preformal problems.
Then of course there’s the heuristic of “it’s fine to shout ‘model uncertainty!’ and hover on the sidelines, but it wasn’t the armchair philosophers who did away with the epicycles, it was Kepler, who was up to his elbows in epicycle data.” One of the big ways that you identify the things that need working on is by trying to solve the problem yourself. By asking how to actually build an aligned superintelligence, MIRI has generated a whole host of open technical problems, and I predict that that host will be a very valuable asset now that more and more people are turning their gaze towards AI alignment.