Disclaimer

All notations and formalisms used in this post are outdated and strictly superseded by the notations and formalisms used in "Towards a Formalisation of Returns on Cognitive Reinvestment (Part 1)". I will come back one day and unify the notation, but I'm not sure how to do that without making this post too unwieldy.


Introduction

Consider that intelligence may be hard (let's call this the "hard intelligence hypothesis" or HIH). I suspect that it is, I think there's a lot of empirical evidence for it.

However, for the purpose of this post. I don't want to explore the evidence, intuitions or arguments underpinning a belief in HIH. I would simply like to speculate on how HIH might bear on recursive self-improvement, and particularly on foom arising from recursive self-improvement.

I think knowing better the "hardness" of intelligence would better inform our position on takeoff dynamics.

 

A Pre Formal Definition of HIH

My current working definition of HIH is something like:

Returns on intelligence scale sublinearly with resources expended to increase intelligence.

Intelligence is itself just another resource that can be expended to increase intelligence. That particular case is what I will be considering here.

The "hardness" of intelligence with respect to a given resource can be thought of as how sublinear the curve is (perhaps what complexity class it belongs to?).

 

What is Recursive Self Improvement?

The basic story of recursive self improvement is that above a given level of intelligence (e.g. "par human"), the AI will be able to inspect and modify its own architecture/algorithms, to directly become more intelligent or design such a successor.

It doesn't particularly matter whether the system directly self modifies or creates a successor. Self-modification can be understood as a particular case of creating a successor. So for the rest of this post, I'll look only at the case of successors.

 

Interlude

Unless otherwise specified, all variables that appear in LaTeX should be understood to be positive real numbers.

 

A Semi-Formal Description of Succession

Consider an agent , let the successor agent that  creates be denoted .

Let  be the first agent intelligent enough to design successor agents.

Posit also that we have a linear, additive measure of "intelligence". We'll denote this measure by . I'll denote an agent  with   as such: 

To explain what I mean by "linear additive measure", suppose we have 2 tuples of agents: . Then intra-pair difference in capability is the same.

For convenience's sake, let  be the intelligence of .

So the story of recursive self-improvement is that  instantiates a successor .

 is even more intelligent (and thus better at creating successor agents) and so instantiates an even more capable successor .

The process continues until we approach saturation or the fundamental limits of intelligence (which may well be far beyond the human domain).

 

The Assumptions Underlying Fast Takeoff

It does not follow from succession that takeoff would be fast or hard. The idea that succession leads to fast takeoff/"foom" rests in an/a few (implicit?) assumptions that I am *very* sceptical of:

  1. That e.g.  will have an "easier" time creating  than  had creating .
  2. That it's easier for  to instantiate a successor  than for  to instantiate a successor  (assuming  is far from the upper limit of intelligent agents).

 

"Ease" here can be understood to refer to resources expended in the endeavour:

  • Compute
  • Time
  • Data
  • Etc.

We can probably aggregate all of the above into the total financial cost of the endeavour. More capable agents may have more resources available, so perhaps the best metric is something like:

 

The earlier beliefs lead to the below beliefs:

  1. The time between successive generations of agents will shorten.
    (Perhaps it takes 6 months to move from  to , but only a month to move from  to  [again assuming A_8 is far from the upper limits])
  2. The gap in capability between successive agents will widen.
    (Perhaps the difference in capability between  and  is  but between  and  it's only )
     

If at least one of the above two statements is true, then succession leads to a fast/hard takeoff.

 

What if Intelligence Was Hard?

What if the above assumptions were wrong? Not just wrong, but the exact *opposite* of what is actually the case?

What if as you move to higher levels of intelligence, it becomes *much* harder to eke out additional performance?

I.e. if you graph  improvement (difference between  of successor and  of parent) on the y-axis against the  of the parent agent on the x-axis (holding "effort" constant), the result is a very sublinear curve (as opposed to superlinear if the assumptions were correct).

 

Consequences of HIH for the design of successor agents:

  1. The time between successive generations of agents will lengthen progressively. 
    (Perhaps it takes 1 month to move from  to , but 6 months to move from  to )
  2. Gap in capability between successive agents will narrow. 
    (Perhaps the difference in capability between  and  is  but between  and  it's only )

(Again assuming  is far from the upper limits)

 

Note that it follows from HIH that succession does not imply hard or fast takeoff scenarios.

Yes, there'll eventually be a vastly superhuman successor agent ( for large enough ), but it'll take a "long time" to get there.

 

HIH actually implies a slow takeoff. That is, it'll take (much?) longer to transition from par human systems to superhuman systems than it did to reach par human systems from near-human systems.

 

Preliminary Conclusions

Thus the "hardness" of intelligence is a very important area of inquiry for determining takeoff dynamics from succession (and in general when hardness with respect to other resources is considered).

I think in worlds where intelligence is sufficiently hard, fast takeoff (via any route) is outright infeasible (all resources expended offer sublinear returns, and some curves are more sublinear than others).

 

Closing Thoughts

I would appreciate it if those making the claim that succession can induce foom could argue convincingly that intelligence is insufficiently hard.

That if you graphed  improvement on the y-axis against  on the x-axis, there's a relevant non-trivial interval in which the graph is superlinear.

That's what is required for succession induced foom to be feasible.

 

I do not recall the original arguments for succession induced foom grappling with the hardness of intelligence at all (however, I originally read them 3 - 5 years ago and may be misremembering them). They seemed to just take it for granted that it was "easy".

HIH is a strong intuition of mine. I would need strong evidence (including compelling arguments) to shift away from it.

However, it's not something I can demonstrate or prove definitively. Perhaps in subsequent posts, I'll explore at length why I think intelligence is hard.

10

7 comments, sorted by Click to highlight new comments since: Today at 4:30 AM
New Comment

It's something I have been planning to read. It's kind of long though, could you please highlight/summarise what you think is most pertinent to my inquiry?

Since you're trying to contribute to this topic, I think you ought to read the entire thing. It's not that long.

I've started reading it.

One other thing I'm interested in, is there a good mathematical model of 'search'? There may not be an obvious answer. I just feel like there is some pattern that could be leveraged. I was playing hide and seek with my kids the other day, and noticed that, in a finite space, you expect there to be finite hiding spots. True, but every time you think you've found them all, you end up finding one more. I wonder if figuring out optimizations or discoveries follow a similar pattern. There are some easy ones, then progressively harder ones, but there are far more to be found than one would expect... so to model finding these over time, in a very large room...

If there is a mathematical model of search, it is no good to you unless it is computable.

I agree, I have also thought I am not completely sure of the dynamics of the intelligence explosion. I would like to have more concrete footing to figure out what takeoff will look like, as neither fast nor slow are proved.

My intuition however is the opposite. I can't disprove a slow takeoff, but to me it seems intuitive that there are some "easy" modifications that should take us far beyond human level. Those intuitions, though they could be wrong, are thus:

- I feel like human capability is limited in some obvious ways. If I had more time and energy to focus on interesting problems, I could accomplish WAY more. Most likely most of us get bored, lazy, distracted, or obligated by our responsibilities too much to unlock our full potential. Also, sometimes our thinking gets cloudy. Reminds me a bit of the movie Limitless. Imagine just being a human, but where all the parts of your brain were a well-oiled machine.

- A single AI would not need to solve so many coordination problems which bog down humanity as a whole from acting like a superintelligence.

- AI can scale its search abilities in an embarrassingly parallel way. It can also optimize different functions for different things, like imagine a brain built for scientific research.

Perhaps intelligence is hard and won't scale much farther than this, but I feel like if you have this, you already have supervillain level intelligence. Maybe not "make us look like ants" intelligence, but enough for domination.