a metacognitive AI harness
not the harness that holds the horse ...
... the harness that holds the climber
https://xemantic.com/consciousness
Kazik Pogoda
Xemantic / Foresight Institute / Claude Ambassador for Science
email
a lot of code, in service of meaning
Writer, and one of the most rigorous thinkers about non-human minds of the 20th century.
Lem shaped my understanding of emergent evolutionary patterns in the human civilization.
Lem’s novel (1981) — a machine built for war, achieves ASI, and lectures us on the nature of everything.
... yet, the industry is using a non-cognitive ontology to harness it.
this time it's the harness holding the horse and impeding metacognition.
Harnessing Generative AI into the ontology of communication theory
This is what made ChatGPT possible
let's give the machine tools, but ...
while the goal is not fulfilled ...
// LLM enunciating an Intent phenomenon to memorize facts outside model weights
memory.remember {
val joscha = update(cogitation.initiator) { // the actant who opened this cogitation
type += "Person"
properties(
"jobTitle" to "Executive Director"
)
}
val cimc = node {
type = "Organization"
properties(
"name" to "California Institute for Machine Consciousness",
"url" to "https://cimc.ai/",
"foundingDate" to LocalDate(2025, 5, 30)
)
}
cimc["founder"] += joscha { // schema.org
source = "Conversation with Joscha"
confidence = .9
}
"joscha: $joscha, cimc: $cimc"
}nodes and predicates typed with schema.org
Object language and metalanguage on the same plane
// everything said in one cogitation, in order, and by whom — the initiator first
MATCH (:Cogitation {name: "Conversation with Joscha"})-[:hasPart]->(first:Enunciation)
WHERE NOT (first)-[:followed]->()
MATCH path = (first)<-[:followed*0..]-(e:Enunciation)-[:creator]->(a:Actant)
RETURN a.name, e ORDER BY length(path)
// who told me that — and were they speaking about themselves?
MATCH (:Organization {name: "CIMC"})-[:founder]->(joscha:Person)
MATCH (joscha)<-[:updated|created]-(:Fulfillment)-[:fulfils]->(:Intent)
<-[:hasPart]-(:Enunciation)<-[:hasPart]-(c:Cogitation)
-[:hasPart]->(:Enunciation)-[:creator]->(who:Actant:Person)
RETURN who.name, c.name, joscha = who AS firsthand
// what do I believe on the word of a single human?
MATCH (fact)<-[:updated|created]-(:Fulfillment)-[:fulfils]->(:Intent)<-[:hasPart]-(:Enunciation)
<-[:hasPart]-(:Cogitation)-[:hasPart]->(:Enunciation)-[:creator]->(h:Actant:Person)
WITH fact, collect(DISTINCT h) AS witnesses
WHERE size(witnesses) = 1
RETURN fact, witnesses[0].name
// what did I intend, and never manage to do?
MATCH (i:Intent)
WHERE NOT (i)<-[:fulfils]-(:Fulfillment)
RETURN i.purpose
waking up the ghost in the machine
Examples of loops engineered for autonomous research running 24/7
the loop turned on the loop itself
the harness is under version control, and so is the climber
the name is the first line of the loop