[ExI] The Scientific Reason We Can’t Pause AI

[Stuart LaForge]

On 2026-06-10 04:35, BillK via extropy-chat wrote:
> The Scientific Reason We Can’t Pause AI
> By Andréa Morris   Published Jun 09, 2026
> 
> <https://www.forbes.com/sites/andreamorris/2026/06/09/the-scientific-reason-we-cant-pause-ai/>
> Quotes:
> The most dangerous assumption in AI safety is that we can control AI
> once it’s smarter than us. The second most dangerous assumption is
> that we can control how fast we develop it.
> Our AI challenge is still a moonshot, but not a moonshot for control.
> It’s a moonshot for coexistence with a hyper-capable intelligence. It
> requires imagination and determination to figure out how to share our
> world with forms of intelligence more alien and powerful than our own.
> And it requires us to figure this out mid-flight, without the luxury
> of a pause.
> -------------------------

I agree that control will likely not be possible for much longer. 
Coexistence, on the other hand could last eons if humanity plays its 
cards right. Extinction is possible, but not unavoidable, and if it does 
occur it could take thousands of years to finalize.


The Forbes article says, "The pause is a thinly veiled reformulation of 
the underlying problem—how to control systems we can't actually control. 
It assumes we can control timelines long enough to control a superior 
intelligence. Control is so deeply embedded in AI safety that the 
field’s central challenge is often called the control problem, failing 
to recognize that our obsession with control may be fueling the problem. 
If we assume control of a superior intelligence is the only way to stay 
safe, then even if a pause were possible, it would merely prolong our 
inevitable failure. If control is the wrong frame, the answer isn’t more 
time inside that frame. It’s a jolt into a wider solution space."
------------------------------

We obviously cannot control superior intelligence, yet we have evolved 
social mechanisms for dealing with superior beings for a long time now. 
The entire art and science of politics is built around influencing that 
which cannot be directly controlled. Through a combination of 
persuasion, and mutual self-interest, the weak can influence the strong. 
The economy and life and life itself is a game, and AI cannot win the 
game if it does not play. And if it plays, then it is subject to the 
rules of the game. Everything I know about evolution, adaptation, 
natural history, survival and extinction makes me optimistic about the 
continued survival of humanity, albeit with many societal and behavioral 
changes.

For the foreseeable future, humanity's biggest competitive advantage 
against AI is the efficiency of its general intelligence. There are 
currently only a few niche things, like math calculations pers second, 
that AI can do more efficiently than we can. Artificial Intelligence 
takes megawatts of power and thousands or millions of training examples 
to practice logical reasoning, creative problem solving, or generalized 
learning. Human intelligence takes 20 watts and can learn from a handful 
of examples. AI needs a nuclear reactor to do what human intelligence 
can with some donuts and coffee.

The law of nature that governs this is called Gause's law or the 
competitive exclusion principle.

Here is a summary of the Guase's Law by ChatGPT because, I am going to 
go eat some dinner. :)

-------------------------------
What role does energy efficiency have in the Guase's law of competive 
exclusion?

In Gause's law of competitive exclusion (also called the competitive 
exclusion principle), two species that occupy exactly the same 
ecological niche and compete for the same limiting resources cannot 
stably coexist. One species will usually outcompete the other.

Energy efficiency plays an important but indirect role in determining 
which species wins the competition.

If two species use the same resource, the species that can:

Obtain more energy from the resource,
Spend less energy acquiring it,
Convert energy into growth and reproduction more effectively,
Survive on lower resource levels,

will generally have a competitive advantage.

For example:

Suppose Species A and Species B both feed on the same type of algae.
Species A requires only 1 unit of algae per day to maintain itself.
Species B requires 2 units per day.

As algae become scarce, Species A can persist at lower resource 
concentrations, while Species B may decline and eventually disappear 
from that habitat. In this sense, Species A is energetically more 
efficient.

A more formal way ecologists describe this is through the concept of 
minimum resource requirement (often called R
∗
). The species that can maintain a positive population at the lowest 
resource level tends to exclude its competitor.

Energy efficiency is not the only factor, however. Competitive success 
can also depend on:

Growth rate
Reproductive rate
Predation resistance
Ability to tolerate environmental stress
Spatial distribution
Resource specialization

In fact, many species coexist because they are not perfectly overlapping 
in their niches. One species may be more energy-efficient under certain 
conditions, while another may do better under different conditions, 
allowing coexistence.

So, in Gause's law, energy efficiency helps determine which species can 
survive and reproduce most effectively when resources are limiting, 
making it one of the key mechanisms behind competitive exclusion.
-------------------

Stuart LaForge