Adap­ta­tion Executors

TagLast edit: 10 Oct 2022 15:40 UTC by aag

Modeling biological systems as Adaption Executors is a central principle of evolutionary biology in general, and evolutionary psychology in particular.

If we regarded human taste buds as trying to maximize fitness, we might expect that, say, humans fed a diet too high in calories and too low in micronutrients would begin to find lettuce delicious and cheeseburgers distasteful. But it is better to regard taste buds as an executing adaptation—they are adapted to an ancestral environment in which calories, not micronutrients, were the limiting factor. And now they are simply executing that adaptation—evolution operates on too slow a timescale to re-adapt to such a recent condition.

Evolution is ultimately just a historical-statistical macrofact about which ancestors did in fact reproduce. These genes then execute again, as they did previously. And so the behavior of the organism is often better interpreted in terms of what worked in the past, rather than what should work in the future. The organism’s genes are, in fact, the causal result of what worked in the past, and certainly not a causal result of the future.

External links

See also

Selec­tion vs Control

abramdemski2 Jun 2019 7:01 UTC
168 points
25 comments11 min readLW link2 reviews

Satis­ficers want to be­come maximisers

Stuart_Armstrong21 Oct 2011 16:27 UTC
38 points
70 comments1 min readLW link

The Power of Agency

lukeprog7 May 2011 1:38 UTC
112 points
78 comments1 min readLW link

Evolu­tion­ary Psychology

Eliezer Yudkowsky11 Nov 2007 20:41 UTC
97 points
42 comments5 min readLW link

The Cog­ni­tive Costs to Do­ing Things

lionhearted (Sebastian Marshall)2 May 2011 9:13 UTC
49 points
21 comments4 min readLW link

Is Mo­ral­ity Given?

Eliezer Yudkowsky6 Jul 2008 8:12 UTC
34 points
100 comments8 min readLW link

The en­emy within

Roko5 Jul 2009 15:08 UTC
22 points
18 comments3 min readLW link

[SEQ RERUN] Adap­ta­tion-Ex­ecu­tors, not Fit­ness Maximizers

MinibearRex23 Oct 2011 2:55 UTC
9 points
0 comments1 min readLW link

The Evolu­tion­ary-Cog­ni­tive Boundary

Eliezer Yudkowsky12 Feb 2009 16:44 UTC
51 points
29 comments3 min readLW link

Adap­ta­tion-Ex­e­cuters, not Fit­ness-Maximizers

Eliezer Yudkowsky11 Nov 2007 6:39 UTC
148 points
33 comments3 min readLW link

Mo­ti­va­tions, Nat­u­ral Selec­tion, and Cur­ricu­lum Engineering

Oliver Sourbut16 Dec 2021 1:07 UTC
16 points
0 comments42 min readLW link

De­liber­a­tion Every­where: Sim­ple Examples

Oliver Sourbut27 Jun 2022 17:26 UTC
27 points
3 comments15 min readLW link

Hu­mans aren’t fit­ness maximizers

So8res4 Oct 2022 1:31 UTC
49 points
46 comments5 min readLW link

Dep­re­cated: Some hu­mans are fit­ness maximizers

Shoshannah Tekofsky4 Oct 2022 19:38 UTC
6 points
22 comments6 min readLW link

Mo­ti­vat­ing Align­ment of LLM-Pow­ered Agents: Easy for AGI, Hard for ASI?

RogerDearnaley11 Jan 2024 12:56 UTC
23 points
4 comments39 min readLW link

Could evolu­tion pro­duce some­thing truly al­igned with its own op­ti­miza­tion stan­dards? What would an an­swer to this mean for AI al­ign­ment?

No77e8 Jan 2023 11:04 UTC
3 points
4 comments1 min readLW link

7. Evolu­tion and Ethics

RogerDearnaley15 Feb 2024 23:38 UTC
3 points
6 comments6 min readLW link

self-im­prove­ment-ex­ecu­tors are not goal-maximizers

bhauth1 Jun 2023 20:46 UTC
14 points
0 comments1 min readLW link

Not an­other bias!

Lionel5 Jun 2023 17:50 UTC
3 points
0 comments1 min readLW link

A study on depression

vlad.proex13 Oct 2020 15:43 UTC
21 points
1 comment9 min readLW link

Cyn­i­cism in Ev-Psych (and Econ?)

Eliezer Yudkowsky11 Feb 2009 15:06 UTC
37 points
40 comments4 min readLW link

Reli­gion as Goodhart

shminux8 Jul 2019 0:38 UTC
21 points
6 comments2 min readLW link

If it looks like util­ity max­i­mizer and quacks like util­ity max­i­mizer...

taw11 Jun 2009 18:34 UTC
20 points
24 comments2 min readLW link

Rep­re­sen­ta­tive democ­racy awe­some­ness hypothesis

taw18 Jun 2009 3:02 UTC
4 points
13 comments2 min readLW link

Some real ex­am­ples of gra­di­ent hacking

Oliver Sourbut22 Nov 2021 0:11 UTC
15 points
8 comments2 min readLW link
No comments.