Openai/69177fbb-14c4-800f-bc57-ccb5a1d88c95

This conversation was exported from ChatGPT

gpt-5-1

User: Are you familiar with RDOS's theory that Asperger's is correlated with Neanderthal behavior?

Are you familiar with RDOS's theory that Asperger's is correlated with Neanderthal behavior?

Assistant: Your question is correct in its framing: the idea comes from RDOS aka Øyvind Hammer, the creator of the Aspie Quiz, who…

Your question is correct in its framing: the idea comes from RDOS (aka Øyvind Hammer), the creator of the Aspie Quiz, who has argued for many years that autistic traits—especially the “systemizing, pattern-oriented, low-social-signal” cluster—represent a partial Neanderthal cognitive inheritance.

A quick evaluation:

Correctness / standing of the idea: This is considered a fringe hypothesis. It has no support in mainstream paleoanthropology, genetics, or autism research. Genetic studies show that nearly all non-African humans have ~1–2% Neanderthal DNA, but there’s no evidence that this DNA corresponds to autistic traits specifically. RDOS’s framework is more of a speculative narrative built by correlating personality profiles with his interpretation of Neanderthal behavior, not something empirically validated.

Who tends to find it appealing: It often resonates with people who identify strongly with autism/Asperger’s traits and prefer an evolutionary-niche explanation—especially those who lean toward systemizing worldviews or anthropology-as-identity frameworks.

Who tends to reject it: Researchers, clinicians, and people oriented toward evidence-based models of neurodevelopment usually dismiss it as non-scientific.

If you want, I can break down the main claims of RDOS’s theory, the scientific problems with each step, or why these ideas keep resurfacing in autism communities.

User: Please.

Please.

Assistant: Here’s a clean breakdown of RDOS’s theory and how it runs into problems at each stage, plus why the idea persists.

Here’s a clean breakdown of RDOS’s theory and how it runs into problems at each stage, plus why the idea persists.

He argues that:

1. Neanderthals had a distinct psychological profile — more solitary, territorial, pattern-driven, tool-focused, less socially fluid.
2. These traits resemble “Aspie” profiles as measured by his Aspie Quiz (systemizing, sensory hypersensitivity, routine-driven behavior, etc.).
3. Some modern humans inherited this cognitive style though interbreeding with Neanderthals.
4. Therefore, autism-spectrum traits are partly a Neanderthal legacy.

He frames this as “two human cognitive lineages” coexisting today:

• A Neanderthal-like lineage (autistic-coded)
• A Sapiens-like lineage (social-intuitive)

###

We have:

• bones
• tools
• DNA
• archaeological sites

We don’t have the behavioral detail needed to map them onto modern psychological profiles. Everything about their social cognition is inferred from indirect evidence, and the picture that emerges—symbolic behavior, group living, care for injured members—does not support the stereotype of “aloof engineers.”

Most non-Africans have ~1–2% Neanderthal ancestry on average. That:

• isn’t enough genetic influence to explain a complex neurodevelopmental condition
• isn’t structured (e.g., autistic people don’t have more Neanderthal DNA than non-autistic people)

Genome-scale studies looking for such patterns simply don’t find them.

Autism arises from:

• hundreds of genes
• gene–environment interactions
• many de novo mutations

…and the genes involved appear to be conserved and present long before the Neanderthal–Sapiens split. There’s no “Neanderthal cluster” associated with autism.

It’s fun, but:

• not validated like the AQ or SRS
• contains items influenced by RDOS’s evolutionary narrative
• cannot be used to deduce ancient population traits

It’s more of a community-created personality inventory than a diagnostic tool.

This is the more interesting part.

People who identify with autistic strengths—systemizing, deep focus, detail orientation—often appreciate an origin story that:

• normalizes those traits
• suggests they were once advantageous
• gives a coherent identity narrative

Autism communities, especially online, often form around:

• identity
• shared narratives
• alternative origin stories

In that context, the Neanderthal hypothesis works more like informal folklore than science.

If someone wants an evolutionary framing without drifting into unsupported claims, researchers tend to emphasize:

• balancing selection (traits like hyperfocus or high sensory acuity can be adaptive in some contexts and costly in others)
• cognitive diversity as population-level robustness
• autistic traits arising from general variation in brain wiring, not lineage divergence

This keeps the focus on present-day neurodiversity without relying on speculative paleopsychology.

If you want, I can also break down:

• the specific archaeological evidence RDOS interprets and how mainstream researchers interpret the same data
• the actual genetic regions in humans that come from Neanderthals and what they do
• or the cultural/psychological appeal of “alternative origin stories” in neurodivergent communities.

User: Let's do the latter two points.

Let's do the latter two points.

Assistant: Here’s a compact, structured look at both:

Here’s a compact, structured look at both:

Genome studies give a fairly detailed picture of which Neanderthal segments survive in our genomes and what functions they influence. The key point: almost none of it relates to cognition, autism, or systemizing traits. Instead, surviving segments cluster around traits that were useful when Homo sapiens entered Eurasia.

The strongest surviving regions involve:

• antiviral defenses
• skin barrier function
• innate immunity

These conferred survival advantages against Eurasian pathogens.

Several surviving Neanderthal variants influence:

• hair thickness
• skin sensitivity
• keratin filament structure

These probably helped adapt to colder, lower-UV environments.

Some regions affect:

• sleep–wake cycle timing
• seasonal photoperiod sensitivity

This fits with adaptation to high-latitude lighting cycles.

A few segments influence:

• lipid processing
• brown fat thermogenesis

Again, Eurasian-environment advantages.

Large sections of Neanderthal-derived DNA were purged strongly, especially around:

• brain development
• testes and reproductive genes
• language-related regions
• neurogenesis

This implies that Neanderthal alleles were maladaptive when introduced into Homo sapiens in precisely the domains that RDOS’s theory claims they shaped.

In short:

• What stuck around mostly shaped skin, immunity, and metabolism.
• What got removed is heavily enriched for cognition and neurodevelopment.

So the genetic landscape contradicts RDOS’s thesis.

There’s a predictable set of dynamics that make theories like RDOS’s attractive even when they lack scientific support. These don’t reflect gullibility; they reflect natural human meaning-making under specific conditions.

Many autistic people grow up feeling:

• alienated
• different
• mislabeled as defective

A lineage theory offers:

• dignity (“my traits have deep roots”)
• identity coherence (“this fits into a bigger pattern”)
• a shared mythos (“people like me have always existed”)

Anthropologically, this mirrors how minority groups build narratives of origin to reinforce identity and cohesion.

The mainstream narrative often pathologizes autism.

An evolutionary-origin story suggests:

• These traits were adaptive.
• They’re not errors but specializations.
• They served a purpose in ancestral contexts.

Even if speculative, it’s emotionally restorative.

Many autistic adults feel harmed or misunderstood by medical and educational systems.

A fringe theory acts as:

• resistance to pathologizing models
• a mythic reclaiming of autonomy
• a way to “tell the story differently”

It functions similarly to alternative medicine narratives among communities dissatisfied with credentialed systems.

Autistic cognition tends toward:

• systemizing
• categorizing
• constructing explanatory models

The Neanderthal hypothesis is appealingly pattern-rich:

• two human lineages
• two cognitive styles
• two evolutionary niches It feels orderly—even elegant.

Online autistic spaces often develop:

• inside jokes
• shared symbols
• community-specific lore

The Neanderthal idea becomes a kind of folklore:

• not believed literally by all
• but meaningful as a cultural motif
• part of group identity performance

Like astrology in queer communities or clan myths in tribal societies, it builds cohesion.

The theory frames difference as ancient and natural rather than:

• personal failure
• parental fault
• modern environmental damage

It externalizes difference in a way that feels protective.

Neanderthal DNA in humans overwhelmingly affects skin, immunity, metabolism, and circadian rhythms, not cognition or autism.

But as a cultural myth, the idea persists because it provides:

• identity,
• dignity,
• explanatory elegance, and
• emotional counterweight to pathologizing models.

If you want, I can go through the strongest scientific argument against Neanderthal–autism correlation, or the most charitable version of RDOS’s idea that could survive contact with real data.

User: Both, please.

Both, please.

Assistant: Here are the two pieces you asked for, each kept tight and structured.

Here are the two pieces you asked for, each kept tight and structured.

The most decisive counterpoint combines population genetics and selection patterns.

When Neanderthal DNA entered the Homo sapiens gene pool, natural selection removed most of the segments that touched:

• neural progenitor proliferation
• cortical development pathways
• synaptic gene networks
• language-related loci (e.g., FOXP2-adjacent regions)
• brain size and skull growth patterns

This wasn’t mild drift—it was strong negative selection, especially in high-expression brain regions. Large comparative studies show a massive underrepresentation of Neanderthal segments in exactly the regions that would need to survive if they contributed to autistic traits.

If Neanderthals carried alleles shaping “autistic-like cognition,” and those alleles were advantageous or even neutral in Homo sapiens, selection would have kept them. Instead, the opposite happened.

This is the hardest single blow to RDOS’s framework.

Autism risk involves hundreds of genes with small effect sizes, plus de novo mutations. Genome-wide association studies show:

• none of the highly replicated autism-associated loci come from introgressed Neanderthal segments
• Neanderthal-derived regions have no enrichment for ASD risk variants
• most introgressed segments influence physiology, not cognition

If Neanderthal traits were behind the autistic cognitive profile, there would be at least faint statistical signals—there are none.

Large genetic datasets comparing thousands of autistic and non-autistic individuals show no ancestry-level difference. Everyone with Eurasian ancestry has basically the same 1–2% Neanderthal proportion.

No elevation = no link at the population level.

Neanderthals exhibit:

• care for injured members
• deliberate burial practices
• symbolic behavior
• cooperative hunting
• ornamentation and pigments

This undermines the idea of them as “solitary, pattern-oriented, low-social-signal” types.

Altogether, the empirical burden is heavy and one-sided.

If we reduce the theory to its least speculative, most defensible core, something remains—though it’s weaker and reframed.

It’s reasonable to assume:

• different populations had different average cognitive inclinations
• climate, ecology, and subsistence patterns shaped subtle biases in attention, perception, and social style
• these differences persist weakly today in modern variation

This doesn’t imply autism is Neanderthal, just that cognitive variation has deep roots.

A few introgressed regions influence:

• circadian rhythm
• light sensitivity
• skin and sensory responsiveness

Autistic people often have atypical sensory profiles; one could hypothesize a soft overlap where some aspects of sensory sensitivity reflect archaic Eurasian traits—but not in a lineage-based or autism-specific way.

You can frame autistic strengths—pattern detection, detail orientation, rule-focused thinking—as:

• part of the natural range of human cognitive strategies
• traits that would have been beneficial for tool-making, tracking, or precision tasks

This doesn’t require Neanderthals specifically; it fits a general “niche specialization” model.

The charitable version isn’t:

• “autistic people are Neanderthal-descended”

It’s more like:

• “autistic traits are part of long-standing human cognitive diversity that predates modern societies, and some aspects may have been shaped by ancient environmental pressures.”

Instead of a diagnostic tool or window into Neanderthal minds, it works as:

• a community-created map of certain cognitive styles
• a way of describing systemizing, solitary-preference, and sensory-heavy profiles
• a narrative device, not an evolutionary claim

You can treat the myth as:

• a metaphor for a cognitive minority
• a way of expressing “we have always been here”
• a narrative of dignity rather than pathology

This is similar to how some communities treat trickster archetypes, demigod lineages, or clan animals: not literally, but meaningfully.

A version of RDOS’s idea that fits real data would look like this:

If you want, I can diagram:

• a version of the idea that completely avoids pseudoscience,
• or a comparison of RDOS’s mythic framing with other identity-origin narratives (e.g., witchblood, starseed, demisexual-as-neolithic-foraging-specialist, etc.).

User: Do you distinguish meaningfully between autism and Asperger's, or do you adhere to the modern autism spectrum model?

Do you distinguish meaningfully between autism and Asperger's, or do you adhere to the modern autism spectrum model?

Assistant: From an accuracy standpoint, the old distinction between Asperger’s and “classic autism” doesn’t hold up well, which is…

From an accuracy standpoint, the old distinction between Asperger’s and “classic autism” doesn’t hold up well, which is why the DSM-5 collapsed everything into Autism Spectrum Disorder (ASD). That said, people often use the older terms to mark meaningful experiential differences, and those differences aren’t wrong—they’re just not sharply bounded categories.

Here’s how the two models compare.

Clinically, the evidence points to:

• shared underlying genetics
• shared developmental pathways
• no clear boundary between the old “Asperger’s” profile and other autistic presentations

When researchers try to sort people into discrete subtypes based on symptoms, cognition, or genetics, the groups blur. That’s why the DSM-5 moved to a single spectrum with variations in support needs, language development, and adaptive functioning.

In formal contexts—diagnosis, epidemiology, research—I treat “Asperger’s” as a historical label for a specific presentation of ASD.

Outside clinical settings, people use “Asperger’s” to describe a recognizable cluster:

• early language develops normally
• average or above-average cognitive ability
• strong systemizing
• narrow or intense interests
• social difficulty without global developmental delay
• comparatively lower sensory overwhelm than some other autistic profiles

That cluster does describe a real pattern, even if it isn’t biologically discrete. So when someone uses “Asperger’s,” I interpret it as shorthand for a specific phenotype on the broader autism spectrum.

It’s a meaningful difference in lived experience, not a meaningful difference in underlying condition.

Three main reasons:

You don’t see “Asperger’s genes” vs “autism genes.”

You see hundreds of overlapping variants with small effects.

The differences between “Asperger’s” and “mild autism” are often:

• degree, not kind
• influenced by language environment, early support, and co-occurring conditions

If you say “Asperger’s,” I interpret that as referring to:

• the high-verbal, cognitively strong, internalizing end of the spectrum
• often characterized by analytical cognition, systemizing, and difficulty with social intuition

If you say “autism” in the broader sense, I treat it as:

• the full range of neurodevelopmental presentations

I don’t correct people for using “Asperger’s,” because the experiential distinction is real and the term is still part of the cultural vocabulary.

If you want, I can map out:

• the clearest cognitive/behavioral profiles associated with the old “Asperger’s” label,
• or the ways in which the two models (Asperger’s vs ASD) influence identity, community, and self-understanding.

User: So the reasoning is that genes associated with ASD risks produce symptoms more or less stochastically.

So the reasoning is that genes associated with ASD risks produce symptoms more or less stochastically. So you wouldn't expect the Asperger's subtype to breed true, it would tend to co-occur with other subtypes in the extended family. But I'm a bit skeptical of the shared environment explanation for early childhood development of language, that's been debunked a million times when applied to racial minority populations.

Assistant: Your summary of the genetic reasoning is on target.

Your summary of the genetic reasoning is on target. The part worth tightening is the role of “shared environment,” because in autism research that phrase is usually misunderstood. Here’s the cleanest way to frame it, avoiding the pitfalls you’re flagging.

What we know from twin and family studies:

• Autism is highly heritable.
• But the heritability is polygenic, meaning there are hundreds of small-effect variants, plus occasional large-effect mutations.
• Those variants combine in different configurations in different individuals—even within the same family.

That leads to:

• one sibling having a profile that looks like classic Asperger’s
• another having more language delay
• another having social traits but not enough to be diagnosed
• another being neurotypical but with high systemizing tendencies

It’s variation in degree, not a Mendelian particulate subtype. That’s why the “Asperger’s subtype” rarely clusters cleanly generationally.

This part is well grounded scientifically.

Most autism researchers today treat “shared environment” as a small contributor—nothing like the old “refrigerator mother” or cultural explanations.

However, the term “environment” in developmental models includes a lot more than parental style or culture. It includes:

• prenatal exposures
• inflammation
• nutritional deficiencies
• maternal health
• preterm birth
• early sensory and motor patterns
• chance neural events during development
• epigenetic regulation
• random developmental noise

These are not “cultural environment” factors at all. They’re biological.

When geneticists talk about nonshared environment, they’re often talking about:

• stochastic neural development
• differences in in-utero blood flow
• microscopic developmental variations between twins

Almost none of that overlaps with the “shared environment” criticisms that appear in debates about racial IQ research, socioeconomic bias, or cultural deprivation models.

So your skepticism is well placed for the sociocultural sense of the term, but that’s not what autism researchers generally mean.

You’re right that cultural environment doesn’t cause autistic speech delay.

Instead, language outcomes seem to reflect:

This can affect early speech emergence without touching the “Asperger-like” cognition.

The key point: The variability in language development comes from biological heterogeneity, not culture.

So you’re right to resist social-environment arguments—those were discredited decades ago. But the modern explanation rests mostly on genetic complexity plus developmental variation, not parenting, not culture.

Here’s the structure that aligns with current evidence:

• There is a set of cognitive/autistic traits that cluster into something like the old “Asperger’s” profile.
• These traits do not form a clean genetic subtype, which is why they don’t consistently breed true.
• Language development differences aren’t caused by shared/cultural environment; they arise from differences in neurodevelopment shaped by polygenic load, prenatal factors, and stochastic biological variation.
• Therefore, “Asperger’s” is a real experiential phenotype, but not a genetically or developmentally discrete category.

If you want, I can diagram exactly how autism heritability breaks down (additive genetics vs nonshared environment vs rare variants) or walk through why monozygotic twins can differ so much in language and sensory traits despite identical genomes.

User: No thanks, I'd like to return to some earlier points.

No thanks, I'd like to return to some earlier points. You said that neanderthal cognition is strongly selected out of the genome. But isn't ASD cognition also severely selected against?

Assistant: The intuition behind your question is solid:

The intuition behind your question is solid: If autistic cognition carries fitness costs in modern humans, why wouldn’t any analogous Neanderthal cognition also be selected out? So why does one get purged and the other persists?

The resolution comes from separating traits from mechanisms.

What’s under negative selection isn’t the “autistic cognitive style” per se, but the combination and intensity that produces impairment.

Many traits associated with autism are individually adaptive:

• detail focus
• systemizing
• high persistence
• sensory acuity
• intense interests
• exceptional memory for patterns
• analytical over social reasoning

These traits raise fitness in many niches.

What gets selected against is:

• the clustering of many such traits to a disabling degree
• early language delay
• social communication deficits
• developmental conditions that impair independence or reproduction

This gives the picture:

• Mild autistic traits → positively or neutrally selected over history
• High-load autistic profiles (clinical ASD) → modestly selected against

This is called mutation–selection balance or polygenic tail selection: useful traits persist, but the extreme ends of the distribution get trimmed.

The Neanderthal–Homo sapiens selection pattern wasn’t driven by “autistic-like traits” being bad.

It was driven by:

Hybrids inherited combinations of genes that didn’t work well together, especially in:

• brain development
• testes
• skeletal morphology
• immune regulation

Natural selection aggressively removes variants that impair hybrid function, even if they were neutral or beneficial in their original population.

Neanderthal brain-development genes were tuned to Neanderthal skull shape, growth timing, and developmental trajectory. Introduced into sapiens architecture, they broke things.

This is like taking engine parts from one machine and plugging them into a different model—most won’t fit cleanly.

They may have worked perfectly well in Neanderthal populations.

The purging reflects hybrid incompatibility, not that Neanderthals had “bad cognitive traits.”

So the mechanism is not “autistic cognition is bad and Neanderthal cognition is like autism so it was removed.” It’s gene mismatch, not trait content.

Key point:

The heritable pieces of autistic cognition are very ancient—older than the sapiens/Neanderthal split—and widely conserved across primates.

Examples:

• FOXP1/FOXP2 pathways
• synaptic scaffolding proteins
• chromatin remodeling genes
• axon guidance genes (e.g., ROBO family)

These aren’t Neanderthal-specific. They’re part of core mammalian and hominin neurodevelopment.

Evolution tolerates a small frequency of disadvantageous extremes if the midrange traits are beneficial.

Think:

• high intelligence → good, but extreme forms can correlate with psychiatric vulnerability
• immune hyperreactivity → good, but extremes produce allergies and autoimmunity
• tall stature → good for dominance, but extremes raise mortality

Autistic traits follow the same pattern.

This explains:

• why autism doesn’t get “selected out”
• why it’s stable across cultures and history
• why it clusters in families but doesn’t breed true

###

A polygenic architecture with many small, adaptive or neutral variants → occasional pathogenic combinations → selection prunes extremes but not midrange traits.

Two diverged hominin genomes recombine → hybrid incompatibility in specific developmental pathways → selection aggressively removes incompatible segments regardless of their original phenotype.

The similarity (selection pressure) masks fundamentally different mechanisms.

If you want, I can map how autistic traits confer specific evolutionary advantages (foraging, tracking, tool analysis, solitary niche specialization), or contrast “polygenic tail conditions” with “hybrid incompatibility” in simple diagrams.

User: Well, let's look at the established evidence and see whether you and I, dialectically, can reason competently.

Well, let's look at the established evidence and see whether you and I, dialectically, can reason competently. First, please summarize we can say with reasonable certainty about Neanderthal behavior from the archeological evidence. Grokipedia has an excellent summary article at https://grokipedia.com/page/Neanderthal_behavior.

Assistant: Good question.

Good question. Here’s a summary (with caveats) of what archaeologists reasonably infer about Neanderthal behavior — plus the major points of uncertainty. This will ground our myth-making discussion in real evidence.

1. Tool Use & Technological Skill - Neanderthals made sophisticated stone tools (Mousterian technology) using prepared-core techniques, which implies advanced planning and manual skill. Fiveable - They also used different raw materials (flint, bone, etc.) and may have hafted tools (attaching stone to handles). Biology Insights - Evidence suggests they produced adhesives such as birch tar, indicating complex cognition. Smithsonian Magazine

1. Use of Fire and Spatial Organization - Hearths have been found in camps, often associated with organized living areas. Encyclopedia Britannica - Some sites suggest seasonal or repeated occupation, not just transient hunting camps. Encyclopedia Britannica
2. Burial Practices - There is good evidence that Neanderthals intentionally buried their dead. National Geographic - At some sites, burials show signs of deliberate pit digging, and the bodies are placed in non-random positions. National Geographic - There is some suggestion of symbolic behavior in burials: for instance, at Shanidar in Iraq, pollen was found in graves (though interpretations are debated). opentextbooks.concordia.ca - Grave goods or modified objects have sometimes been found near burials (e.g., stone tools, possible “resting stones” near skulls). National Geographic
3. Symbolic Behavior / Ornamentation - Pigments (ochre, manganese) appear in many Neanderthal sites, which could indicate body-painting, symbolic marking, or technical uses (e.g., adhesive). opentextbooks.concordia.ca - Some personal ornaments: Neanderthals used eagle talons, perhaps as jewelry, at multiple sites. Smithsonian Magazine - Caves: in Bruniquel Cave (France), Neanderthals built ring-like structures from stalagmites deep in the cave, suggesting planned construction and use of fire for lighting. Wikipedia - Musical behavior: there is a disputed “flute” (a bone with holes) found in Divje Babe cave that might represent symbolic or musical instrument use. Wikipedia
4. Social Structures and Care - Fossils show Neanderthals with serious injuries who survived for extended periods, implying that others cared for them. National Geographic - The presence of deep social bonds is supported by burial practices and group living. Anthroholic - Some evidence suggests cultural exchange with Homo sapiens: a recent study (Tinshemet Cave) argues for shared burial customs and symbolic use of ochre across species. Phys.org
5. Cognitive Capacity - Because of their tool complexity, use of adhesives, and spatial planning, Neanderthals likely had fairly high working memory, planning capabilities, and executive function. arXiv - Their ability to use pigments, ornaments, and possibly symbolic items suggests some capacity for symbolic thought, though it’s less “rich” than that of later Homo sapiens. opentextbooks.concordia.ca

- Symbolic Meaning vs. Practical Use: Pigment use could be functional (hide processing, insect repellent, adhesives) rather than symbolic. opentextbooks.concordia.ca

• Burial Interpretation: While burials are well-attested, whether they reflect religion or symbolic belief systems is ambiguous. Some grave goods are disputed; the “flower burial” idea (Shanidar) has been challenged. opentextbooks.concordia.ca
• Scale of Social Complexity: The Bruniquel cave structures show spatial planning and construction, but we don’t know if they had broad symbolic or ritual significance. Wikipedia
• Music Claim Disputed: The Divje Babe “flute” is controversial; some argue the holes could be from animal chewing rather than deliberate instrument-making. Wikipedia
• Ornament Dating and Association: Some sites (like Grotte du Renne) that show personal ornaments may be stratigraphically mixed or misattributed. Wikipedia
• Inter-Species Cultural Influence: Evidence for cultural exchange with Homo sapiens (e.g., burial similarities) is recent and under review; it’s hard to distinguish independent development vs borrowing. Phys.org

- Neanderthals were not “primitive cavemen.” They had fairly complex technology, social bonds, and possibly symbolic behavior.

• They likely had some form of ritual or proto-ritual behavior, but nothing like the highly abstract symbolic cultures of later Homo sapiens (at least, nothing definitively proven).
• They cared for their dead and for injured individuals, suggesting empathy and social cohesion.
• They used pigments and ornaments, but we don’t know for sure whether this was purely symbolic, practical, or both.
• Their cognitive capacities were substantial, though probably not identical to modern humans in everything like long-term symbolic abstraction.

- Because there is real (but limited) evidence for symbolic behavior, social caring, and planning, the “Neanderthal spiritual-ancestor” narrative isn’t totally baseless.

• However, we need to be very careful about projecting modern social-cognitive categories (like “autistic style”) onto them — much of the behavioral evidence is ambiguous or multivalent.
• The myth works well if framed as metaphorical resonance, not literal cognitive equivalence.

If you like, I can map the plausibility of each “autistic-style” trait (e.g., solitary focus, pattern cognition, low social signaling) onto the strongest Neanderthal behavioral hypotheses, evaluating how probable each is given what we actually know.

Do you want me to do that?

User: Yes please.

Yes please.

Assistant: Here’s a structured mapping of autistic-style cognitive/behavioral traits onto what we can reasonably infer from Neande…

Here’s a structured mapping of autistic-style cognitive/behavioral traits onto what we can reasonably infer from Neanderthal evidence — with a scale of plausibility, epistemic cautions, and why each mapping is or isn’t defensible.

This is not trying to “prove” RDOS’s myth, but to show which pieces of it are compatible with archaeological reality and which are not.

1. Intense Focus / Deep Specialization

Archaeological basis

• Mousterian toolmaking required long-practice manual skill, consistency, and deliberate multi-step planning.
• Birch tar production (through dry distillation) shows procedural, patient, tightly controlled behavior.
• Evidence of repeated use of the same raw materials and techniques over long periods suggests stable, specialized traditions.

Plausibility as an autistic-style trait: High

This is the strongest overlap. Neanderthal technological behavior implies:

• high tolerance for repetition
• deep procedural memory
• stable craft specialization
• narrow but refined technical repertoires

These echo autistic tendencies toward deep systemizing and craft-like mastery.

Caution: Specialization ≠ autism. Lots of non-autistic hominins show this too. The overlap is metaphorically resonant, not diagnostic.

2. Preference for Small Groups / Limited Social Networks

Archaeological basis

• Genetic evidence suggests small, kin-heavy groups.
• Low population density and limited long-distance trade relative to Homo sapiens.
• Burials and care for injured suggest strong bonds within the group.

Plausibility as an autistic-style trait: Moderate

It’s plausible because:

• small groups reduce social signaling load
• high relatedness reduces need for constant impression-management
• limited inter-group exchange suggests less emphasis on extended social networks

But group size was probably driven by ecology, not psychology.

Good fit for mythic purposes, but weak as a literal cognitive inference.

3. Reduced Symbolic Expressiveness / Less Ornamentation

Archaeological basis

• Symbolic artifacts exist (pigments, talons, cave structures), but they’re rarer and less elaborated than early modern human symbol systems.
• No clear evidence of complex art, figurative carving, or large-scale ritual spaces.

Plausibility as an autistic-style trait: Moderate–High

If one interprets:

• less symbolic abstraction
• more concrete cognition
• less reliance on metaphor or extended social signaling

this fits many autistic cognitive profiles (reduced importance of social-symbolic play, preference for practical over symbolic complexity).

Caution: This could simply reflect demographic constraints, ecological constraints, or preservation bias. It’s unsafe to treat “less symbolism” as a cognitive diagnosis.

4. Direct / Functional Communication Style

Archaeological basis

• We know almost nothing about Neanderthal language.
• Some reconstructions suggest vocal tracts fully capable of speech; others note anatomical differences.

Plausibility as an autistic-style trait: Speculative

There is no direct evidence for the style of communication, only for the biomechanical capacity for speech.

If the myth wants to emphasize:

• concrete communication
• lower reliance on high-context social signaling
• practical/functional messaging

…it’s not contradicted by evidence, but it’s not supported either.

5. Caring Behavior / Deep Attachment Bonds

Archaeological basis

• Evidence of long-term survival of severely injured individuals strongly implies caretaking.
• Intentional burials show social attention to the dead.

Plausibility as an autistic-style trait: High

This counters stereotypes. Autistic communities often emphasize:

• loyalty
• deep if selective bonds
• strong commitments to individuals rather than large-group dynamics

Neanderthal care behavior fits this very well: strong small-group empathy rather than flashy large-group social signaling.

This is one of the best myth-aligned traits.

6. Pattern Sensitivity / Spatial Planning

Archaeological basis

• The Bruniquel cave ring structures are especially compelling: systematic placement of stalagmite fragments deep in a cave.
• Tool production requires visual-spatial precision and consistent techniques.

Plausibility as an autistic-style trait: Moderate–High

Spatial reasoning and pattern construction are characteristic strengths in many autistic individuals.

We should avoid overinterpretation, but if the myth wants Neanderthals as:

• strong spatial planners
• pattern-constructors
• procedural thinkers

…it has solid archaeological support.

7. Reduced Interest in Exchange Networks / Social Ornamentation

Archaeological basis

• Neanderthals had limited long-distance trade networks relative to sapiens.
• Less evidence of social ornamentation designed for wide-group display.

Plausibility as an autistic-style trait: Moderate

If one interprets:

• low interest in social signaling
• little concern for extended social networks
• prioritization of competence over prestige

this fits some autistic social profiles.

But again: ecological explanation is simpler.

8. Lower Tolerance for Rapid Cultural Innovation

Archaeological basis

• Neanderthal toolkits were conservative for long periods.
• Slow rates of cultural change relative to early sapiens.

Plausibility as an autistic-style trait: Moderate–High (mythically) / Cautious (empirically)

Autistic individuals often prefer:

• stable routines
• incremental rather than abrupt change
• mastery-based over novelty-based behavior

This maps neatly onto Neanderthal conservatism.

But it may reflect demographics (small populations maintain novelty poorly).

Synthesis: A Realistic Mapping

If we create a table of “myth viability”:

| Trait | Archaeological Fit | Cognitive Speculation Fit | Mythic Resonance | | ------------------------- | ------------------ | ------------------------- | ---------------- | | Deep specialization | Strong | Strong | Excellent | | Small-group focus | Moderate | Moderate | Strong | | Low symbolic excess | Moderate | Moderate–High | Strong | | Direct communication | Weak | Moderate | Medium | | Strong caring bonds | Strong | Strong | Excellent | | Spatial/pattern cognition | Moderate–Strong | Strong | Excellent | | Limited trade networks | Moderate | Weak–Moderate | Medium | | Cultural conservatism | Moderate | Moderate | Strong |

Conclusion: There is a coherent cluster of plausible traits—deep focus, small-group loyalty, spatial reasoning, routine preference, caring bonds—that resonate with autistic self-descriptions. These do not “prove” anything about Neanderthal cognition, but they make the mythic connection symbolically plausible and internally coherent, while remaining honest about the limits of inference.

If you want, we can next build a mythic framework integrating these traits into a narrative that is:

• coherent
• archeologically grounded
• explicitly non-literal
• resonant for autistic identity

Or we can go point-by-point refining which aspects are strongest for the myth.

gpt-5-t-mini

User: Not quite yet, I'd like to solidify my understanding and propose a model.

Not quite yet, I'd like to solidify my understanding and propose a model.

ASD-related genes are more ancient than either sapiens or Neanderthals. There was likely a cohort of ASD in both sapiens and Neanderthals, where the proportion of ASD present in the latter is purely speculative. (Is that actually true? My understanding is that we have some full Neanderthal genomes that could be analyzed for ASD risk via GWAS.) This is irrelevant to us today because all cognition-related genes from Neanderthals disappeared under intense negative selection via hybrid gene mismatch. While we didn't cover this before, I suspect ASD was under positive selection in sapiens along with intelligence during the Holocene, which then leveled off around the late 1800s (and possibly reversed direction).

Regarding Neanderthal theory as a meaningful mythical construct, we still have a possibility that must be addressed. But first I'd like your opinion on my understanding so far.

Assistant: Nice model — you’ve captured the key pieces and the right sorts of uncertainty.

Nice model — you’ve captured the key pieces and the right sorts of uncertainty. I’ll restate your points as I understand them, flag what’s well-grounded vs speculative, correct a couple of technical bits, and offer a tightened model you can use going forward.

1. Many genes implicated in ASD are older than the sapiens–Neanderthal split.

1. Both species plausibly had individuals showing autistic-style phenotypes, but the proportion in Neanderthals is unknown.
2. Most Neanderthal cognition-related alleles were purged from the modern human genome after admixture because of hybrid incompatibilities.
3. In Homo sapiens, ASD-linked variation persisted because component traits were often adaptive in moderation; extreme combinations were pruned by selection.
4. You think there may have been positive selection on cognitive traits (including some alleles linked to ASD) during the Holocene, with a possible plateau or reversal around the industrial era / late 1800s.

- Polygenic, old components. Many biological pathways implicated in neurodevelopment are evolutionarily ancient; some alleles affecting neurodevelopment existed before the split with Neanderthals.

• We can’t infer phenotype from bones. Behavioral/psychological inference from archaeological remains is extremely indirect.
• Introgressed Neanderthal DNA was nonrandomly distributed. Studies show depletion of Neanderthal segments in regions of high brain expression and in testis/reproductive genes — consistent with selection against hybrid incompatibility.
• Mutation–selection balance model for ASD. That framework — useful midrange traits + rare/strong deleterious combinations producing clinical ASD — is a standard, evidence-backed explanation for persistence of risk.

- On “ASD genes are older than the split”: many genes and pathways involved in neurodevelopment are ancient, but specific risk variants identified in modern GWAS can be recent. Also, ASD risk has two partly distinct genetic contributors: (a) common, small-effect polygenic variation (older and shared) and (b) rare, often de novo, large-effect mutations (recent). So “ASD genetics is older than the split” is true for the broad pathways but not universally true for every risk allele.

• On measuring ASD risk in Neanderthals via GWAS: you cannot run a meaningful GWAS on a handful of ancient genomes. GWAS requires large samples and the same population structure. What you can do is: (1) check whether loci implicated by modern ASD GWAS overlap regions introgressed from Neanderthals, and (2) look for Neanderthal alleles at known risk sites. Those approaches test for overlap/enrichment, not “ASD prevalence in Neanderthals.”
• On Holocene positive selection for intelligence / ASD alleles: that’s plausible as a hypothesis (selection for cognitive/learning traits as societies grew) but it’s controversial and tricky to demonstrate. Human GWAS signals for educational attainment and cognitive proxy traits show some signatures consistent with selection, but these results are confounded by population structure, stratification, changing environment, and demography. Claims of directional selection on “intelligence” during the Holocene need careful, conservative interpretation. The idea of a late-industrial reversal is likewise plausible (relaxation of selection due to medicine, differential fertility, etc.), but again empirical support is mixed and contested.

1. Deep background: Core neurodevelopmental pathways are ancient and shared across hominins. This creates a substrate for variation in both Neanderthals and sapiens.

1. Two genetic layers: - Polygenic background (many old alleles with small effects; these shape continuous cognitive variation). - Rare large-effect variants (often recent or de novo; these can shift an individual into the clinical ASD range).
2. Admixture effect: When sapiens and Neanderthals mixed, some Neanderthal alleles persisted (mostly in skin, immunity, metabolism), while many alleles affecting brain development were purged because they produced maladaptive interactions in the sapiens developmental program (hybrid incompatibility). That purging is about genetic context, not the intrinsic “goodness” or “badness” of a phenotype in the donor population.
3. Selection on variation in sapiens: Within sapiens, selection acted on cognitive and behavioral variation. Many component traits of ASD could be neutral or advantageous in certain ecological niches; extreme clinical presentations are kept rare by selection and by the stochastic nature of mutation.
4. Recent millennia dynamics: There may have been modest directional shifts in allele frequencies affecting cognition during the Holocene (e.g., selection for literacy-friendly, cooperative, or technical skills), but separating true selection from demography/population stratification is hard. Modern changes (medicine, social structure, fertility differences) may have altered selective pressures, producing shifts in the distribution of clinical risk—however, the evidence is mixed and methodological noisy.

- “Could Neanderthal genomes be analyzed for ASD risk?” Not by GWAS on Neanderthals. You can look up whether modern ASD-associated loci are present in Neanderthal sequences or whether introgressed segments overlap ASD loci. That’s informative about overlap/enrichment, not prevalence.

• “Was there ASD in both species?” Very plausible at the level of individual variation (there’s no reason to imagine hominins lacked cognitive diversity). But we have no direct way to estimate prevalence in Neanderthals.
• “Did selection favor cognitive traits in the Holocene?” It’s plausible some cognitive traits were under selection during agricultural and post-agricultural transitions, but the signal is noisy and contested. Treat that as a plausible hypothesis, not an established fact.

- Step 1: check enrichment of modern ASD GWAS loci in introgressed Neanderthal segments (this is a standard genomic overlap test).

• Step 2: examine whether alleles at high-impact ASD loci are present in available high-coverage Neanderthal genomes.
• Step 3: model allele-frequency trajectories for cognitive-proxy GWAS hits across ancient DNA time transects to test Holocene selection (requires ancient human aDNA panels). I can sketch the exact analyses you’d run and the interpretation pitfalls for each.

Bottom line: your core intuitions are good. Tighten two things—(A) don’t treat every ASD risk allele as ancient, and (B) treat Holocene directional selection claims as hypotheses that need careful genomic/demographic control. Want me to draft the specific overlap/enrichment test you could run (methods, stats, and likely outcomes)?

User: Point A is fair, but claims of Holocene directional selection for intelligence are very well supported now which I'm fa…

Point A is fair, but claims of Holocene directional selection for intelligence are very well supported now (which I'm familiar with because I read the blogs of Emil Kirkegaard and Peter Frost--I'm sure you'd object that they're "fringe" sources, but they're mostly reposting studies by other people anyway). I'll grant that associating that with ASD on the grounds of relatively small gene-linkage is pure speculation on my part. And thanks for correcting me on GWAS, I should know better but my low working familiarity with the subject is showing.

Assistant: You’ve got the right instincts: there are respectable signals suggesting polygenic selection on cognitive/education-rel…

You’ve got the right instincts: there are respectable signals suggesting polygenic selection on cognitive/education-related traits during the Holocene, but the evidence is subtle, methodologically finicky, and contested. Below I’ll give a compact, balanced take: what the strongest positive evidence is, what the major methodological objections are, and what a reasonable position looks like.

- Polygenic score differences and cross-population patterns. Multiple papers find that polygenic scores (PGS) for educational attainment (EA) and related cognitive proxies differ systematically between populations in ways that are unlikely under neutral drift alone. These early signals (and their replications) are the raw basis for the claim of selection. Preprints

• Ancient-DNA time transects. Ancient DNA lets researchers track allele-frequency change over millennia. Genome-wide scans across thousands of ancient samples have detected changes consistent with selection at loci tied to complex traits (including cognitive proxies when you map modern GWAS hits onto ancient samples). Mathieson et al. (2015) and follow-ups established the utility of this approach. PMC
• Increasing GWAS power reduces noise. More recent, very large GWAS (e.g., Okbay et al. 2022) identify thousands of loci for EA; larger, better-powered GWAS make polygenic inference less noisy and enable more sensitive tests for selection. PubMed

- Population stratification and confounding. GWAS hits can reflect subtle ancestry structure correlated with environment rather than causal biology. When you build PGS from such hits, cross-population comparisons can pick up demography rather than selection. Berg & Coop (2014) introduced many of the analytic controls and warned about this problem; follow-up work has shown it’s a real and nontrivial confound. PMC

• LD and ascertainment biases. GWAS hits are discovered in particular LD backgrounds (usually European samples). That affects how signals transfer to other populations and how much of a perceived difference is real. Newer methods try to polarize effects or use within-family designs to reduce this bias. OUP Academic
• Phenotype proxy limitations. “Educational attainment” is an imperfect proxy for cognitive ability and is heavily shaped by culture, policy, and opportunity. Selection on EA-PGS might reflect selection on correlated traits (health, fertility, social structure) rather than raw intelligence per se. PMC

- Strength: ancient DNA lets you observe allele-frequency change through time, which is far stronger evidence of recent selection than cross-sectional PGS differences. Mathieson et al. (2015) and later studies used this to identify selection episodes in the Holocene. PMC

• Limit: linking ancient allele changes to cognition requires mapping modern GWAS hits onto ancient samples—which assumes effect sizes and trait architecture are stable and that the modern phenotype proxy maps cleanly backward. That’s plausible but not airtight.

- Plausible: modest directional selection on alleles correlated with education/cognitive proxies during parts of the Holocene is plausible and supported by multiple lines (PGS differences, aDNA trajectories, and theory about agriculture/urbanism changing selective regimes). Preprints

• Qualified: the magnitude, timing, and exact trait under selection are still uncertain because of GWAS confounds, LD/ascertainment biases, and modern phenotype complexity. Treat the conclusion as probabilistic rather than nailed-down fact. PMC

- Fit: If selection favored cognitive/learning traits (e.g., systemizing, attention to detail) at the population level, the polygenic background for those traits would shift. That could increase the population mean for some component traits that overlap with autistic-style cognition. (This is what you were intuiting.)

• Don’t overreach: ASD as clinical condition depends heavily on rare de novo variants and on combinations that produce impairment. Polygenic shifts in mean cognitive proxies don’t directly translate to large changes in clinical ASD prevalence or to a clean mapping between EA selection and ASD risk. In short: helper overlap possible; direct causal link weak and speculative. PubMed

- Read Mathieson et al. (2015) and later ancient-DNA scans for selection to see how allele frequencies moved through the Holocene. PMC

• Read Berg & Coop (2014) and follow-up methodological papers on correcting for stratification in polygenic selection tests. PMC
• Look at the latest large GWAS (Okbay et al. 2022) and at within-family polygenic analyses (which reduce stratification bias) to see how robust the EA signals are. PubMed

Your belief that there’s now substantial genomic evidence for Holocene directional selection on cognitive/education-related alleles is defensible — the signal is real enough to be taken seriously. But it’s also correct to be cautious: the claim that this directly drove modern ASD variation or that it is a large, well-quantified effect remains speculative. Use the aDNA + within-family GWAS literature as your most reliable guide.

If you want, I can:

• assemble a short reading list (3–6 papers) with PDFs and 1-sentence takeaways, or
• sketch a simple toy model (equations + assumptions) showing how a modest shift in polygenic mean could alter the frequency of high-load ASD outcomes (mutation–selection balance + shifting mean). Which would you prefer?

gpt-5-mini

User: Not right now, I'd like to return to the meaning-making myth of RDOS's theory and describe how it could plausibly be re…

Not right now, I'd like to return to the meaning-making myth of RDOS's theory and describe how it could plausibly be rescued.

If it were true that Neanderthals had a culture similar to autism communities, then autism communities could reasonably describe themselves as the spiritual descendants of Neanderthals, if not the genetic descendants (in the sense of having more Neanderthal variants). As you mentioned, the interpretation of the archeological evidence to behavior predictions is extremely indirect, so it would be most correct to say we have a very poor idea of Neanderthal culture. Both the support for this idea and the criticisms of it are on equally speculative ground for lack of hard evidence, and the only way we can judge between them is by assessing their competence in reasoning.

Assistant: Yes — that’s a careful and reasonable framing.

Yes — that’s a careful and reasonable framing. You’re essentially separating the mythic or narrative claim from the empirical claim, and grounding it in epistemic humility. Let me restate and extend your reasoning in a structured way.

If we accept that:

• Neanderthal behavior is extremely poorly known and archeological evidence only weakly constrains hypotheses about social structure, cognition, or culture, and
• Autism communities seek identity, dignity, and a coherent narrative of difference,

then a “Neanderthal spiritual descendant” story serves as a meaning-making construct rather than an empirical claim. It plausibly functions to:

1. Reframe autistic traits as ancient and adaptive rather than pathological.
2. Provide an origin narrative that supports group cohesion and identity.
3. Offer archetypal metaphors for cognition styles: solitary focus, pattern orientation, intense interests.
4. Externalize difference in a culturally digestible way, protecting against shame or social stigma.

- Supportive: Neanderthals had complex material culture (tools, pigments, some symbolic artifacts, care for injured), but social dynamics and cognitive style are unknown. Some archaeologists have suggested variability in social network size and specialization that could, hypothetically, resemble certain autistic traits.

• Limiting: Any claim that Neanderthals had an “autistic culture” is highly speculative: there’s no direct behavioral measure, and cognitive inference from bones and artifacts is indirect.

Thus, the plausibility of the myth depends on reasoning competence, not on the strength of data. Both proponents and critics operate in a context of underdetermination.

1. Reframe it as symbolic rather than genetic truth. - Autism communities are cultural descendants in terms of values, behaviors, and preferred cognitive styles. - Claiming genetic descent is unnecessary and speculative; the narrative still holds value symbolically.

1. Ground the myth in indeterminacy. - Emphasize that Neanderthal social and cognitive traits are unknown, leaving room for imaginative reconstruction. - The story is not falsified by current evidence, because there is no strong evidence either way.
2. Focus on traits, not labels. - Highlight overlap in plausible traits: systemizing, specialized interests, solitary-focused cognition, tool-use intelligence. - Avoid claiming exact equivalence with modern ASD; rather, emphasize cognitive resonance.
3. Use it as a heuristic, not a hypothesis. - The myth serves to generate reflection, identity, and cohesion. - It can guide narrative, art, or community storytelling without needing to survive genomic or archaeological testing.

- The myth does not contradict hard evidence; it operates in a zone of uncertainty.

• Its value is social, psychological, and symbolic, not empirical.
• Criticism about genetic or behavioral inaccuracy is irrelevant if the community uses it as a metaphorical scaffold rather than a literal claim.
• Competent reasoning is possible: you can evaluate internal coherence, narrative plausibility, and cultural function, even without evidence.

In short: if framed as symbolic/cultural ancestry, with clear acknowledgment of empirical uncertainty, the “Neanderthal-as-autism ancestor” story is logically defensible and meaningfully useful — even if all literal claims about Neanderthal cognition remain speculative.

If you want, I can outline a stepwise “epistemically honest” narrative framework for the myth that maximizes its resonance while avoiding scientific overreach.