[ExI] They're Made out of Meat

[John Clark]

On Thu, May 28, 2026 at 4:49 PM BillK via extropy-chat <
extropy-chat at lists.extropy.org> wrote:

 > *I **asked Gemini to explain the percentages and the
> conclusion.Basically, Gemini said that it is because the maths is working
> with insufficient information.*


*Thanks for calling my attention tothat paper (**Dissolving the Fermi
Paradox <https://arxiv.org/pdf/1806.02404>) **by Anders Sandberg, Eric
Drexler and Toby Ord; even though it was written in 2018 somehow I had
never heard of it before. We already know what Gemini thinks about it, so I
asked GPT his opinion:*
==
*GPT*:  "The paper you linked is *“Dissolving the Fermi Paradox”* by Anders
Sandberg, Eric Drexler, and Toby Ord.

The central argument of the paper is:

The apparent contradiction known as the *Fermi paradox* may not actually be
a paradox at all once we properly account for our enormous uncertainty
about how likely intelligent life is to arise.

The usual Fermi paradox

The paradox is often phrased as:

   - The universe contains an enormous number of stars and planets.
   - Even if intelligent life is rare, there should still be many
   civilizations.
   - Therefore we “should” see evidence of extraterrestrials.
   - But we don’t.

This is often summarized as “Where is everybody?”

The paper argues that this conclusion comes from a hidden mathematical
mistake.
------------------------------
The authors’ key point

Most estimates use something like the *Drake equation*, which multiplies
several probabilities together:

   - fraction of stars with planets
   - fraction with habitable planets
   - probability life begins
   - probability intelligence evolves
   - probability civilizations become detectable
   - etc.

The usual treatment plugs in single “best guess” numbers for these
probabilities.

The authors argue this is misleading because some of these quantities
are *profoundly
uncertain* — not just a little uncertain, but uncertain across *many orders
of magnitude*.

For example, we do not know:

   - how hard abiogenesis (origin of life) really is
   - how improbable eukaryotic cells were
   - whether intelligence is common or fantastically rare
   - whether technological civilizations survive long enough to spread

A parameter might plausibly vary not by a factor of 2, but by:

   - millions,
   - billions,
   - or vastly more.

------------------------------
Their mathematical insight

When you multiply many highly uncertain probabilities together, the result
is *not* well represented by plugging in average values.

Instead, the uncertainty distribution becomes extremely broad.

The paper shows that once realistic uncertainty is included, there is
actually a substantial probability that:

   - humanity is the *only technological civilization in the observable
   universe*, or
   - one of very few.

If that is true, then the lack of alien evidence is unsurprising.

So the “paradox” dissolves.
------------------------------
Why this matters

A lot of Fermi paradox explanations assume that because alien civilizations
should be common, something catastrophic must wipe them out, such as:

   - self-destruction,
   - AI doom,
   - resource exhaustion,
   - berserker probes,
   - universal colonization failure,
   - “great filters,” etc.

This paper argues that we may not need such speculative explanations at all.

The simplest explanation may be:

Intelligent technological life is just extraordinarily rare.

------------------------------
An intuitive analogy

Suppose someone says:

“There are billions of lottery tickets sold, so many winners must exist.”

That sounds reasonable — unless the odds themselves are wildly uncertain.

If the odds might secretly be 1 in:

   - 10 million,
   - 10 trillion,
   - or 10^100,

then the expectation changes radically.

The authors claim our uncertainty about life and intelligence is closer to
the second situation.
------------------------------
The paper’s broader philosophical message

The paper is really about *uncertainty propagation*.

It argues that people often become overconfident when multiplying together
uncertain estimates. Using precise-looking numbers can create an illusion
of knowledge.

In reality:

   - we only have one known biosphere,
   - one known example of intelligent life,
   - and essentially no statistical sample.

So confidence that the universe “should” be full of civilizations may be
unjustified.
------------------------------

The authors explore several different uncertainty models and ask what
happens when you honestly propagate those uncertainties through the Drake
equation.

Their results are surprisingly large.

They conclude that under what they regard as “reasonable” uncertainty
assumptions:

   - the probability that humanity is the only technological civilization
   in the Milky Way can be on the order of tens of percent, and
   - the probability that we are the only technological civilization in the
   entire observable universe can still be non-negligible — sometimes
   around a few percent.

One of their headline examples gives roughly:

   - about 30–50% chance we are alone in the galaxy
   - and around 10–20% chance we are alone in the observable universe

depending on the assumptions used.

The exact numbers vary across the models in the paper.
------------------------------

What shocked many readers was not the exact percentages, but the fact that
the numbers are nowhere near zero.

Before this paper, many discussions implicitly assumed:
P(we are alone)≈0

The authors argue instead that, because the uncertainties are so enormous,
probabilities like:
P(alone in galaxy)∼0.3

or even
P(alone in observable universe)∼0.1

are entirely compatible with current knowledge.
------------------------------

An important subtlety:

The paper is not saying:

“We probably are alone.”

Rather, it says:

“Current scientific knowledge does not justify high confidence that the
universe should be crowded with civilizations.”

That is a much more cautious claim.
------------------------------

Another interesting point from the paper is that the authors include the
effect of:

   - the Great Silence itself,
   - failed SETI searches,
   - and the lack of visible galactic engineering.

Including those observations increases the probability that civilizations
are rare.

In Bayesian terms, the silence updates the probability distribution toward
sparsity.
------------------------------

One reason the observable-universe probability can still be surprisingly
high is that the Drake equation contains several factors that may each be
extraordinarily tiny.

For example:
N=R∗fpneflfifcL

If even one factor is astronomically small — say the probability of
abiogenesis or intelligence — then multiplying by the huge number of
planets may still not produce many civilizations.

The paper emphasizes that we simply do not know those factors well enough
to rule this out.
One especially important implication

The paper weakens the argument that silence itself is evidence of doom.

If civilizations are already expected to be extremely sparse, then:

   - no radio signals,
   - no Dyson spheres,
   - no galactic empires,
   - and no probes

are not especially mysterious.
------------------------------
In one sentence

The paper argues that the Fermi paradox largely disappears once we honestly
account for how little we know about the probability of intelligent life
arising."

=========
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20260529/eeeeca34/attachment-0001.htm>