Asiantuntijan mukaan tekoälyn pitäisi kiinnostaa kaikkien alojen ihmisiä, ja kaikilla pitäisi olla mahdollisuus opiskella sitä.
”Ei tekoäly ole mikään luonnonvoima, joka tulee jostakin ulkopuolelta.”
Tämä tarina nimenomaan näyttäisi vahvistavan sitä pelkoa siitä,että kohta me emme enää voikaan tehdä sanataidetta tai runoilla, vaan meidän täytyy asentaa ilmastointi-putkia, samalla kun tekoäly käskee meitä asentamaan niitä. Ja tämä on tietysti pelottavaa.
Itse ajattelen optimistisemmin, ehkä jonkun mielestä sinisilmäisesti. Näen asian niin, että tekoäly ja teknologia ovat edelleen työkaluja. Ihmiset päättävät edelleen sen, mihin me niitä haluamme soveltaa. Ei tekoäly ole mikään luonnonvoima, joka tulee jostakin ulkopuolelta.
Samalla tavalla voidaan ajatella markkinataloutta. Siinäkin on mekanismeja, jotka ikään kuin ulkoistavat markkinavoimat ihmisten käsien ulkopuolelle jonkinlaisiksi luonnonlaeiksi. Eihän se niin ole.Niissäkin on kyse poliittisista päätöksistä, joille koko markkinatalous on alisteinen.
Uskoisin, että teknologia voidaan siinä mielessä nähdä tavallaan markkinamekanis-meja vastaavana ilmiönä, jolle kyllä voidaan tehdä ja tehdäänkin koko ajan jotain.
Teknologian sääntelystä puhutaan usein pessimistisesti.Ajatellaan, että tekno- logia kehittyy sääntelyä nopeammin ja että kun sääntelyä on vihdoin saatu aikaan, on teknologia jo kehittynyt eteenpäin.
Kyseenalaistan tämänkin ajatuksen. Sääntely on ylipäänsä kuuma peruna tai pikem-minkin matopurkki, josta on hirveän vaikeaa keskustella jalat maassa ja faktapohjai-sesti. Se,että tekoälyn sääntely olisi jo vanhentunutta syntyessään,esitetään jotenkin väistämättömänä faktana, ja siinä ei oikein kyseenalaisteta sitä, että onko todella näin? Se taas totta kai palvelee teknologiajättien etuja siinä mielessä, että se naker-taa esimerkiksi EU:n ja sen jäsenvaltioiden kykyä ja mandaattia reguloida. Googlel-la, Metalla ja Microsoftilla on valtavat koneistot, joiden tehtävä on nimenomaan hidastaa sääntelyä ja asettaa kaiken maailman kapuloita rattaisiin.

– Tekoälystä puhuttaessa ääneen pääsevät vain insinöörit tai minun kaltaiseni nörtit, vaikka siinä keskustelussa pitäisi kuulua myös juristien, sosiologien ja muiden yhteiskuntatieteilijöiden ääni, Teuvo Roos sanoo. Kuva: Emma Grönqvist
Esimerkiksi EU:n yleisen tietosuoja-asetuksen eli GDPR:n kaltainen lainsäädäntö on aivan älyttömän hienoa, ja sitä ei tule edes oikeastaan ajatelleeksikaan, niin kauan kuin se on voimassa ja kaikki on hyvin.
Olin juuri tentaattorina Johdatus tekoälyyn -kurssilla. Opiskelijoiden piti lukea EU:n sivuilta tekoälyyn liittyvää materiaalia ja esimerkiksi uusi tekoälyasetus, joka oli kesäkuussa parlamentissa äänestettävänä. Siellä oli lause, jossa sanottiin, että EU:n tekoälyasetus luo ensimmäistä tekoälyalaa sääntelevää lainsäädäntöä.
”Ei oikeastaan ole totta, että lainsäädäntö syntyisi vanhentuneena.”
Tentissä kysyttiin, että koska EU:n komission sivuilla todetaan näin, niin se varmaan-kin tarkoittaa sitä, että tekoälyä ei sääntele tällä hetkellä mikään lainsäädäntöpaketti. Joten voisivatko opiskelijat siis esimerkiksi huijata tässä tentissä ja käyttää siihen tekoälyä? Pyysin opiskelijoita pohtimaan, tarkoittaako se todella tätä.
No, eihän asia ole niin. Halusin korostaa sitä, että tekoälyä koskeva sääntely ei tule kertaheitolla puhtaalle pöydälle jonain futuristisena olentona.Se on väärä lähtökohta, koska meillähän on jo lainsäädäntöä, joka koskee myös tekoälyä.
Kerron esimerkin: jos minulla olisi itseajava auto, joka kaistanvaihdon yhteydessä ajaa pyöräilijän päälle, on se tietenkin rikos, vaikka ei olekaan olemassa lakia, joka erikseen kieltää tekoälyä ajamasta ihmisten päälle. Ei siinä vaiheessa voi sanoa, että ”tekoäly teki sen”.
Tai sitten vaikkapa ihmisten yksityisyydensuojan loukkaaminen tai deepfake-videoilla tehdyt mustamaalauskampanjat. Eihän niitä saa tehdä. Ei siis oikeastaan ole totta, että lainsäädäntö syntyisi vanhentuneena.
Olen tunnistanut julkisesta keskustelusta kaksi tapaa puhua tekoälystä. Toi-nen niistä on teknologiaoptimistinen, jossa puhutaan uudesta teknologisesta vallankumouksesta, joka tulee mullistamaan kaiken.
Toinen sitten on alarmistinen tapa, jossa puhutaan riskeistä: siitä, että jäämme kohta kaikki työttömiksi ja meistä tulee tekoälyteknologian omistavien yhtiöi-den orjia. Nämä ovat kaksi täysin erilaista keskustelua, jotka eivät ole juuri vuorovaikutuksessa keskenään. Mitä mieltä olet tästä?
Totta kai,näin se on.Tämä kysymys on kysytty minulta jo useamman kerran parin vii-me päivänkin aikana. Tällaisessa ongelma kuitenkin on se, että siinä ajatellaan, että tekoäly on nyt joku tällainen aivan uusi ja ihmeellinen juttu, jota ei ole aikaisemmin millään lailla ollut ja joka ilmestyy jostain toiselta planeetalta.
Tällaisella utopia-dystopia-akselilla keskustellessa unohdetaan tekoälyn arkisuus ja sen olemassa olevat,tämänhetkiset vaikutukset. Kuten esimerkiksi se,miten tekoälyn hyödyt jakautuvat hyvin, hyvin epätasaisesti,ja ne voivat kasvattaa esimerkiksi talou-dellista ja alueellista epätasa-arvoa. Se, että jos tekoälystä ajatellaan scifi-tasolla, se tekee hankalaksi keskustella jo tapahtuneista asioista, niistä tylsemmistä puheenaiheista kuten siitä, kenelle tekoälyn luoma hyvinvointi kasautuu.
On pidettävä mielessä esimerkiksi kaikki tekoälyn taustalla oleva ”klikkityö”, jossa ih-miset tuottavat dataa tekoälylle ja ”opettavat” tekoälyä tunnistamaan kuvia klikkaile-malla esimerkiksi ”linja-autoa” esittäviä kuvia muiden kuvien joukosta. Nämä ihmiset saavat siitä naurettavan pientä palkkaa, joka ei riitä elämiseen.
Tällainen työ ei kehitä näiden ihmisten osaamista yhtään mihinkään suuntaan vaan tavallaan orjuuttaa heitä. He joutuvat elämään syklissä, jossa he eivät pysty opiske-lemaan tai elämään normaalia elämäänsä tai edes kunnollista vuorokausirytmiä. He vain klikkailevat.
”Haluaisin, että ei ajateltaisi tekoälyn olevan jotain tulevaisuuden outoa visiota.”
Toinen esimerkki on ChatGPT:stä. Sen ”opettamiseen” on käytetty ihmisten palautet-ta. Tekoäly tuottaa tekstiä, ja ihmiset arvioivat,oliko se hyvä vai huono vastaus. Oliko siinä vihapuhetta tai väkivaltaan yllyttämistä, ja niin edespäin. Sillä on hienosäädetty ChatGPT:tä.
Sitä työtä oli teetetty kenialaisilla työntekijöillä aivan surkealla palkalla, ja ne ihmiset olivat joutuneet katsomaan ja lukemaan sieltä aivan todella sairasta vihapuhetta ja väkivaltaista tekstiä,joka oli hyvin traumatisoivaa näille työntekijöille. Palkkaus ja korvaukset tästä hommasta olivat täysin naurettavia. Kaikki tämmöiset esimerkit ovat vähän ”tylsiä”, jos vertaa siihen että voidaan heittää ilmoille ajatus kiiltävästä robotista, joka tulee ja vie kaikkien työpaikat.
Sen takia olen huolissani siitä,että mediassa narratiivi on keikahtanut niin paljon pois näistä asioista, joissa on oikeasti todella tärkeitä, akuutteja ongelmia. Niistä on myös paljon asiantuntemusta eri paikoissa yhteiskuntaa.
Silti tekoälystä puhuttaessa ääneen pääsevät vain insinöörit tai minun kaltaiseni nörtit, vaikka siinä keskustelussa pitäisi kuulua myös juristien, sosiologien ja muiden yhteiskuntatieteilijöiden ääni.
Viimeinen kysymys. Mitä meidän kaikkien olisi hyvä pitää mielessä tekoälystä?
Korostaisin sitä, että se ei ole mitään tosi outoa scifiä, joka näyttää aivoilta sinisessä virtapiirissä.Haluaisin,että ei ajateltaisi tekoälyn olevan jotain tulevaisuuden outoa vi-siota, vaan että se on jo nyt arjessa käytettäviä älylaitteita,jotka ovat täynnä tekoälyä käyttäviä sovelluksia. Ne vaikuttavat ihmisten ja heidän perheidensä elämään jo nyt.
Tekoäly ei ole mitään käsittämätöntä rakettitiedettä,vaan jokainen voi sitä ymmärtää, jos haluaa. "
***
TÄLLAISTA HEWOMPASKAA SILLÄ KAJAANIN _TEKOLYLLÄ LYKÄTÄÄN!!!
https://hameemmias.vuodatus.net/lue/2019/09/vaara-teoria-kielen-synnysta
" perjantai, 6. syyskuu 2019
Ukrainalainen ”Maidan-HP-tieteilijä”…
...
... Näin "meillä":
http://keskustelu.skepsis.fi/Message/FlatMessageIndex/403774?page=1#405104
Tampereen valeyliopiston haistapaskantiedehöntät eivät halua edes kuulla todellisesta ihmistymisestä mitään
https://www.is.fi/tiede/art-2000007931688.html
Suomalaistutkijat selvittivät: Homo sapiens peittosi neandertalilaiset luovuusgeenien avulla
Tutkijan mukaan luovuusgeenit ovat auttaneet ihmisiä selviämään koronaviruksen kaltaisista vitsauksista.

Terho "Hörhö" Lehtimäki johti "tutkimusta" Liisa Keltingans-Järvisen kanssa. Kuva: Timo Marttila (ilmekin vaikuttaa höyrähtäneeltä)
Mikko Marttinen
5:41 | Päivitetty 5:42
Homo sapiens on paitsi viisas ihminen, myös luova ihminen.
Tämä selviää Tampereen yliopiston tutkijoiden uudesta tutkimuksesta, jonka tulokset on julkaistu arvostetussa Nature-sarjan Molecular Psychiatry -lehdessä.
Geenitutkimus perustuu suomalaisen Lasten ja nuorten sepelvaltimotaudin riskiteki-jät -tutkimuksen (LASERI) ainutlaatuiseen aineistoon, jota verrattiin simpanssien ja neandertalinihmisten DNA:han.
Tutkijat tunnistivat aineistosta 267 tunnepohjaiseen reagoivuuteen, itsehillintään ja itsetietoisuuteen vaikuttavaa geeniä, jotka löytyvät vain nykyihmisistä.
– Nämä geenit todistavat,että luovuuden kehittyminen oli Homo sapiensin evoluution ja elossa säilymisen salainen ase, jota serkuillamme neandertalinihmisillä ei ollut, professori Terho Lehtimäki sanoo Tampereen yliopiston tiedotteessa.
– Tämä huomionarvoinen geenilöytö avaa ensimmäistä kertaa ikkunan menneisyy-teemme ja valaisee käsitystämme itsetietoisuutemme kehityksen tärkeästä roolista ihmisen evoluutiossa.
Lehtimäen mukaan ainutlaatuiset geenit säätelevät prosesseja,joiden ansiosta nykyihmiset ovat sosiaalisia, luovia kertovassa taiteessa ja tieteessä sekä sukulaislajejaan vastustuskyisempiä ikääntymistä, vammoja ja sairauksia vastaan.
Sen jälkeen, kun Homo sapiensit muuttivat Afrikasta noin 60000 vuotta sitten, he syrjäyttivät vähitellen neandertalinihmiset ja muut ihmislajit. Ne kaikki kuolivat sukupuuttoon noin 40000 vuotta sitten.
– Ihmisen luovuus, sosiaalisuus ja terve pitkäikäisyys syntyivät vastauksena tarpee-seen sopeutua ankariin ja monimuotoisiin olosuhteisiin ja kommunikoida suurissa sosiaalisissa ryhmissä 400000 – 100000 vuotta sitten, Lehtimäki toteaa.
– Tälläkin hetkellä kohtaamme covid-19-pandemian vuoksi samanlaisia haasteita, joihin meidän on sopeuduttava luovasti, kuten esi-isämme oman aikansa haasteisiin.
"Aiheesta" aikaisemmin:
http://keskustelu.skepsis.fi/Message/FlatMessageIndex/401874?page=1#401874
Risto Koivula
15.09.2019 22:03:41
401874 ... "
https://www.kemiamedia.fi/luovuus-auttoi-homo-sapiensia-jaamaan-eloon/
Uutiset | 23.4.2021 | Kemiamedian toimitus
Luovuus auttoi Homo sapiensia jäämään eloon
Siinä missä neandertalilainen ja muut ihmislajit kuolivat noin 40000 vuotta sitten su-kupuuttoon, Homo sapiens säilyi hengissä luovuutensa ja seurallisuutensa ansiosta.
Tähän viittaa Tampereen yliopistossa tehty geenitutkimus.
Tutkijat selvittivät geneettisten verkkojen evoluutiota simpanssista nykyihmiseen ja tunnistivat luovuuden geenit, jotka erottavat meidät muista lajeista.
Geenitutkimus perustuu suomalaisen Laseri-hankkeen (Lasten ja nuorten sepelvaltimotaudin riskitekijät) ainutlaatuiseen aineistoon.
Tutkijat tunnistivat aineistosta 267 tunnepohjaiseen reagoivuuteen, itsehillintään ja itsetietoisuuteen vaikuttavaa geeniä, jotka löytyvät vain nykyihmisistä.
”Nämä geenit todistavat, että luovuuden kehittyminen oli Homo sapiensin evoluution ja elossa säilymisen ’salainen ase’, jota serkuillamme neandertalinihmisillä ei ollut”, sanoo kliinisen kemian professori Terho Lehtimäki yliopiston tiedotteessa. Lehti-mäen ja psykologian professorin Liisa Keltikangas-Järvisen lisäksi projektissa oli mukana tutkijoita muualta Suomesta, Yhdysvalloista ja Espanjasta.
Tulokset julkaisi Nature-sarjan Molecular Psychiatry -lehti.
Löydetyt geenit säätelevät ihmisen sopeutumista
Tutkimuksessa tunnistetut 267 geeniä löydettiin suuremmasta 972 geenin ryhmästä, jonka sama ryhmä oli tunnistanut jo aiemmin.
”Nämä 267 geeniä yhdessä vastaavat lähes kaikista periytyvistä temperamentin ja luonteenpiirteiden vaihteluista, jotka säätelevät ihmisen sopeutumista ympäristössä tapahtuviin muutoksiin”, Lehtimäki kertoo.
Arvaamattomia muutoksia ja uhkia ovat esimerkiksi sosiaaliset konfliktit, tarttuvat taudit, ilmaston muuttuminen ja selviytymiseen tarvittavien resurssien saantimahdollisuuksien heikkeneminen.
Ilmentymisen säätely ratkaisee
Geenit, jotka erottavat nykyihmisen neandertalilaisista ja simpansseista, ovat lähes kaikki RNA:sta valmistettuja säätelygeenejä eivätkä DNA:sta valmistettuja proteiineja koodaavia geenejä.
Sapiensille ainutlaatuisista geeneistä 95 prosenttia ei ole proteiinia koodaavia, vaan niihin liittyy enimmäkseen pitkiä koodaamattomia rna:ita geeniverkossa, joka säätelee ihmisen itsetietoisuutta.
”Homo sapiensin, neandertalinihmisten ja simpanssien proteiineja koodaavat geenit ovat lähes kaikki samanlaisia. Se, mikä siis erottaa nämä lajit toisistaan on niiden proteiineja koodaavien geenien ilmentymisen säätely.”
...
Molecular Psychiatry (2022) 27:354–376
https://doi.org/10.1038/s41380-021-01097-y
E X P E R T R E V I E W
file:///C:/Users/Huawei/Downloads/s41380-021-01097-y.pdf
Evolution of genetic networks for human creativity
I. Zwir 1, 2
C. Del-Val 2
M. Hintsanen 3
K. M. Cloninger 4
R. Romero-Zaliz 2
A. Mesa 2
J. Arnedo 2
R. Salas 5
G. F. Poblete 5, 6
E. Raitoharju 7
O. Raitakari 8
L. Keltikangas-Järvinen 9
G. A. de Erausquin 10
I. Tattersall 11
T. Lehtimäki 7
C. R. Cloninger 1, 4
Received: 30 October 2020 / Revised: 19 March 2021 / Accepted: 31 March 2021 / Published online: 21 April 2021
© The Author(s) 2021. This article is published with open access
C. R. Cloninger
[email protected]
1 Department of Psychiatry, Washington University School of Medicine, St. Louis, MO, USA
2 Department of Computer Science and Artificial Intelligence, University of Granada, Andalusian Research Institute in Data
Science and Computational Intelligence, Granada, Spain
3 Unit of Psychology, Faculty of Education, University of Oulu, Oulu, Finland
4 Anthropedia Foundation, St. Louis, MO, USA
5 The Menninger Clinic,Baylor College of Medicine,and DeBakey VA Medical Center,Houston, TX, USA
6 The Menninger Clinic, Houston, TX, USA
7 Department of Clinical Chemistry, Fimlab Laboratories, and Finnish Cardiovascular Research Center - Tampere, Faculty of Medicine and Health Technology,Tampere University, Tampere, Finland
8 Center for Population Health Research, University of Turku and Turku University Hospital; Research Center of Applied and Preventive Cardiovascular Medicine, University of Turku; Department of Clinical Physiology and Nuclear Medicine, Turku University Hospital, Turku, Finland
9 Department of Psychology and Logopedics, University of Helsinki, Helsinki, Finland
10 Department of Psychiatry, University of Texas San Antonio, Long School of Medicine, The Glenn Briggs Institute of Alzheimer’s and Neurodegenerative Disorders, San Antonio, TX, USA
11 American Museum of Natural History, New York, NY, USA
These authors contributed equally: I. Zwir, C. Del-Val
Supplementary information
The online version contains supplementary material available at
https://doi.org/10.1038/s41380-021-01097-y.
Abstract
The genetic basis for the emergence of creativity in modern humans remains a mystery des-pite sequencing the genomes of chimpanzees and Neanderthals,our closest hominid relatives. Data-driven methods allowed us to uncover networks of genes distinguishing the three major systems of modern human personality and adaptability: emotional reactivity, self-control, and self-awareness. Now we have identified which of these genes are present in chimpanzees and Neanderthals.We replicated our findings in separate analyses of three high-coverage genomes of Neanderthals. We found that Neanderthals had nearly the same genes for emotional reacti-vity as chimpanzees, and they were intermediate between modern humans and chimpanzees in their numbers of genes for both self-control and self-awareness. 95% of the 267 genes we found only in modern humans were not protein-coding, including many long-non-coding RNAs in the self-awareness network. These genes may have arisen by positive selection for the characteristics of human well-being and behavioral modernity, in-cluding creativity, pro-social behavior, and healthy longevity. The genes that cluster in asso-ciation with those found only in modern humans are over-expressed in brain regions involved in human self-aware-ness and creativity, including late-myelinating and phylogenetically recent regions of neocor-tex for autobiographical memory in frontal, parietal, and temporal regions, as well as related components of cortico-thalamo-ponto-cerebellar-cortical and cortico-striato-cortical loops.
We conclude that modern humans have more than 200 unique non-protein-coding genes re-gulating co-expression of many more protein-coding genes in coordinated networks that un-derlie their capacities for self-awareness,creativity, prosocial behavior, and healthy longevity, which are not found in chimpanzees or Neanderthals.
Introduction
One of the most fundamental questions about human nature is what sparked the explosive emergence of creativity in modern humans before their widespread dispersal from Africa and the subsequent extinction of Neanderthals [1–4].
Major controversies persist about the basis for human creativity in art and science, as well as about the differences in cognition, language, and personality that distinguish modern humans from extinct hominids [5–8]. These controversies occur because the archeological and fossil records are incomplete and subject to ambiguous interpretation [9, 10].
What distinguishes behaviorally modern humans from other hominids?
Anthropologists distinguish behaviorally modern Homo sapiens (Sapiens) from other hominids by virtue of Sapiens’ enhanced cognitive, social, and physical adaptability.
Behaviorally modern Sapiens demonstrate remarkable creativity compared to other hominids : that is,they show signs of innovation,flexibility, depth of planning, and related cognitive abilities for symbolism and self-awareness that enable spontaneous generation of narrative art and language [2,5,11-13]. Early behaviorally modern Sapiens were also more prosocial in their behaviors than archaic hominids: they maintained larger social groups, established reci-procal social networks for remote trade, and regularly cooperated with one another in groups composed partially or completely of non-kin, as well as providing altruistic support and cooperation with non-kin who were raising children or disabled [11, 14, 15].
Behaviorally modern Sapiens are also distinguished by their healthy longevity, as evidenced by their resilience to cold and other climatic extremes [16], lower energy requirements and reduced mortality from injury and disease [17–19], and a prolonged post-reproductive life-span that facilitates cooperative breeding [11, 20, 21], which have all enhanced health and viability in diverse, harsh, and unpredictable habitats throughout the world.
The lineages of Sapiens and Homo neanderthalensis (Neanderthals) are thought to have diverged from a common ancestor during the Middle Pleistocene before 500 thousand years ago (kya), at a time when the lineage of Sapiens was isolated in Africa and that of Neander-thals was confined to Europe and western Asia [22,23]. Precursor forms to Neanderthals are recognized at least by 430 kya in Europe [24],but the behaviors and genomes of Neanderthals themselves are best known from artifacts and fossils dating from 130 to 40 kya in Eurasia [Supplementary Information]. In contrast, anatomically modern Sapiens emerged in eastern Africa [22] by 200 to 160 kya [2, 25] following a period from 320 to 200 kya marked by un-predictable climactic fluctuations [15,25,26] that were superimposed on a long-term pattern of progressive aridity [27].Under these challenging ecological conditions, precursors of beha-viorally modern Sapiens began to maintain larger social groups and reciprocal social allian-ces with non-kin (e.g., remote trade networks), express themselves symbolically (e.g., art, or-namentation), collect remote resources (e.g., pigments, obsidian, and other special stones) for later use, flexibly use expanded dietary options (e.g., fishing and collecting shellfish) in times of unpredictable resource availability, and began to accumulate cultural knowledge and standardized technologies that enhanced their adaptability and well-being [15,25,26, 28].
Recent findings, however, suggest that behaviorally modern Sapiens, with a distinctively more imaginative and flexible set of abilities that had not been observed in any hominids there or elsewhere, emerged in Africa about 100 kya and spread throughout the continent thereafter [29].
The ecological and economic pressure on the smaller bands of mobile and muscular hunters in the lineage of the Neanderthals in Europe were different from those on the lineage of Sa-piens in East Africa [30]. Neanderthals and their European ancestors were less resilient to cli-matic extremes,particularly cold,and their hunting of large land animals demanded high daily energy expenditures[31].Nevertheless,Neanderthals were able to function successfully before they had to compete with Sapiens. Neanderthals were able to conserve their reliance on hun-ting large land animals by moving out of inhospitable areas without the need to develop grea-ter social connectedness or more efficient and diverse technologies and resources [17, 22, 28, 31].
The innovative practices of Sapiens are best documented after 50 kya when they flourished to a stage in which the creative imagination of fully modern humans was unmistakably dis-played [2, 5, 32]. The flourishing of behavioral modernity in the late Pleistocene is likely to have been facilitated by incremental cultural and neurobiological processes by which comp-lex behaviors like narrative figural art and language emerged by exaptation and behavioral recruitment [2]. In any case, the basic features of behavioral modernity must have been already present when Sapiens spread out of Africa between 65 and 55 kya, while the African climate became drier and colder [27,33]. The inventive, sociable,and resilient Sapiens were able to adapt well to unpredictable and diverse conditions as they migrated out of Africa and spread throughout the world, replacing all other hominids by 40 kya and producing cultures that flourished by continuing to expand in knowledge,art, science, technology, and population density to the present day.
What is creativity? How is it measured?
The most distinctive and prominent feature of behavioral modernity identified by paleoanth- ropologists and archeologists is what psychologists have described as creativity, particularly the achievements and personality traits of Evolution of genetic networks for human creativity highly creative people.
355
Creativity can be succinctly defined as the use of imagination or original ideas to achieve valued goals [34, 35], and is a multifaceted phenomenon that can be assessed in terms of par-ticular aspects of intelligence and/or particular aspects of personality [36-38].The psychomet- ric tests of the creative aspects of intelligence were developed by Guilford and Torrance to measure aspects of divergent thinking in verbal and pictorial tasks. Divergent thinking is an innovative way of solving problems by exploring many possible solutions, making sponta-neous intuitive connections among what are conventionally regarded as disparate phenomena , while tolerating some ambiguity [39]. Divergent thinking typically occurs in states of restful and playful self-aware evaluation of internal thoughts and images,such as mind-wandering in the default mode, flow, free association, day-dreaming, or contemplation [37, 40- 42], which depends on activation of the media prefrontal cortex for evaluation of internal stimuli as a core component of the self-awareness network [43, 44]. In contrast, convergent thinking fol-lows a logical sequence of inferences to arrive at a single solution with certainty; it depends on the lateral prefrontal and parietal cortices, which are core components of the executive self-control network that supports purposeful use of symbols and intentional inhibition of externally triggered impulses [19, 45, 46].
The features used to measure divergent thinking include originality (inventive and imagina-tive thoughts), flexibility (ability to move from one conceptual field to another), fluency (free-flow of many relevant ideas and responses),elaboration (many vivid, specific details), a high degree of abstraction, and persistence despite uncertainty [39, 47, 48].
Divergent thinking tests developed by Guilford and Torrance are the most widely used tests of creative intellectual functioning because they are strongly predictive of creative achievement and problem-solving ability in everyday life [38, 47, 48].
How is creativity related to other aspects of behavioral modernity?
In addition to its cognitive properties, divergent thinking involves relaxed states of intuitive awareness that are also characterized by physical spontaneity, cheerful affect, playfulness, and sociability [40, 49, 50], which can be quantified in terms of personality characteristics. Personality refers to the way an individual learns to shape and adapt to an ever-changing internal and external environment [51].
Like divergent thinking, creative personality features are multi-faceted, including character traits (i.e.,styles of rational self-government,with executive functions of self-directedness, le-gislative functions of cooperativeness, and judicial functions of self-transcendence) and tem-perament traits (i.e.,emotional drives of curiosity about what is novel,willingness to take risks , willingness to work for social recognition, and perseverance for the sake of achievement) [36, 52, 53]. The two domains of temperament and character make it clear that a person’s potential for creativity cannot develop without both the wisdom to recognize what is valuable and the plasticity to adapt accordingly. The most widely used psychometric test for assessing both domains of the creative personality is the Temperament and Character Inventory (TCI) [51, 52, 54].
Tests of creative divergent thinking in verbal and pictorial tasks, creative personality traits as measured by the TCI,and direct assessments of lifetime creative achievements, are each highly reliable and validated by their strong correlations with one another even when general intelligence and demographic variables are controlled [47, 48]. Empirically, the TCI creative personality profile also measures human health in general, including physical, mental, and social well-being [19, 53, 55].
Put another way, the three domains of features of behavioral modernity identified by anthropologists are in fact interdependent aspects of modern human health and well-being.
As a result, the TCI provides valid quantitative phenotypic measures with which to investi-gate the cognitive, emotional, and social functions, brain connectivity, and genetics underly-ing creativity, prosociality, and other aspects of well-being in modern humans in ways that are robustly replicable [19, 56].
Cognitive scientists have proposed that the creative ability of Sapiens to see the world and other people in new ways depends on several interrelated brain processes of learning and memory. Sapiens’ creativity is thought to depend on human brain functions for prospective learning (i.e., the encoding, storing, and retrieval of intended actions), constructive learning (i.e., recollection of the past and imagining the future),and the related capacities for theory of mind (i.e., the ability to attribute mental states to ourselves and others to facilitate empathic social interaction), the default mode (i.e.,awareness of internal milieu without focus on exter- nal tasks), autobiographical memory (i.e., vivid recollection of past experiences with contex-tual awareness of when and where facts were learned),and story-telling (i.e.,meaningful com- position of narrative figural art and language), which are all aspects of self-awareness and share largely overlapping brain circuitry [57–59]. In turn, these processes underlying diver-gent thinking operate cooperatively with other processes underlying convergent thinking, which have complementary functions for problem-solving in successful daily living [39, 46]. Just as creative personality is multifaceted, its related brain functions are also multifaceted aspects of complex neurocognitive systems of adaptability that are measured by the TCI [19].
357
How do complex adaptive abilities develop and evolve?
... "
***
https://www.nature.com/articles/d41586-023-03272-3
" NEWS
25 October 2023
AI ‘breakthrough’: neural net has human-like ability to generalize language
A neural-network-based artificial intelligence outperforms ChatGPT at quickly folding new words into its lexicon, a key aspect of human intelligence.
Max Kozlov & Celeste Biev

Scientists have created a neural network with the human-like ability to make generalizations about language1. The artificial intelligence (AI) system performs about as well as humans at fol-ding newly learned words into an existing vocabulary and using them in fresh contexts, which is a key aspect of human cognition known as systematic generalization.
The researchers gave the same task to the AI model that underlies the chatbot ChatGPT, and found that it performs much worse on such a test than either the new neural net or people, despite the chatbot’s uncanny ability to converse in a human-like manner.
The work, published on 25 October in Nature, could lead to machines that interact with people more naturally than do even the best AI systems today. Although sys-tems based on large language models, such as ChatGPT, are adept at conversation in many contexts, they display glaring gaps and inconsistencies in others.
The neural network’s human-like performance suggests there has been a “break-through in the ability to train networks to be systematic”,says Paul Smolensky, a cog-nitive scientist who specializes in language at Johns Hopkins University in Baltimore, Maryland.
Language lessons
Systematic generalization is demonstrated by people’s ability to effortlessly use new-ly acquired words in new settings.For example,once someone has grasped the mea-ning of the word ‘photobomb’,they will be able to use it in a variety of situations, such as ‘photobomb twice’ or ‘photobomb during a Zoom call’. Similarly, someone who un-derstands the sentence ‘the cat chases the dog’ will also understand ‘the dog chases the cat’ without much extra thought.
But this ability does not come innately to neural networks, a method of emulating hu-man cognition that has dominated artificial-intelligence research,says Brenden Lake, a cognitive computational scientist at New York University and co-author of the study . Unlike people, neural nets struggle to use a new word until they have been trained on many sample texts that use that word. AI researchers have sparred for nearly 40 years as to whether neural networks could ever be a plausible model of human cognition if they cannot demonstrate this type of systematicity.
A version of the human ability to apply new vocabulary in flexible ways has been achieved by a neural network. Credit: marrio31/Getty
To attempt to settle this debate, the authors first tested 25 people on how well they deploy newly learnt words to different situations. The researchers ensured the parti-cipants would be learning the words for the first time by testing them on a pseudo-language consisting of two categories of nonsense words. ‘Primitive’ words such as ‘dax,’ ‘wif’ and ‘lug’ represented basic, concrete actions such as ‘skip’ and ‘jump’. More abstract ‘function’ words such as ‘blicket’,‘kiki’ and ’fep’ specified rules for using and combining the primitives, resulting in sequences such as ‘jump three times’ or ‘skip backwards’.
Participants were trained to link each primitive word with a circle of a particular colour, so a red circle represents ‘dax’, and a blue circle represents ‘lug’. The resear-chers then showed the participants combinations of primitive and function words alongside the patterns of circles that would result when the functions were applied to the primitives. For example, the phrase ‘dax fep’ was shown with three red circles, and ‘lug fep’ with three blue circles, indicating that fep denotes an abstract rule to repeat a primitive three times.
Finally, the researchers tested participants’ ability to apply these abstract rules by gi-ving them complex combinations of primitives and functions. They then had to select the correct colour and number of circles and place them in the appropriate order.
Cognitive benchmark
As predicted, people excelled at this task; they chose the correct combination of co-loured circles about 80% of the time, on average. When they did make errors, the re-searchers noticed that these followed a pattern that reflected known human biases.
Next,the researchers trained a neural network to do a task similar to the one presen-ted to participants, by programming it to learn from its mistakes. This approach allowed the AI to learn as it completed each task rather than using a static data set, which is the standard approach to training neural nets. To make the neural net human-like, the authors trained it to reproduce the patterns of errors they observed in humans’ test results. When the neural net was then tested on fresh puzzles, its answers corresponded almost exactly to those of the human volunteers,and in some cases exceeded their performance.
By contrast,GPT-4 struggled with the same task,failing, on average, between 42 and 86% of the time, depending on how the researchers presented the task. “It’s not ma-gic, it’s practice,” Lake says. “Much like a child also gets practice when learning their native language, the models improve their compositional skills through a series of compositional learning tasks.”
Melanie Mitchell, a computer and cognitive scientist at the Santa Fe Institute in New Mexico, says this study is an interesting proof of principle, but it remains to be seen whether this training method can scale up to generalize across a much larger data set or even to images. Lake hopes to tackle this problem by studying how people develop a knack for systematic generalization from a young age, and incorporating those findings to build a more robust neural net.
Elia Bruni, a specialist in natural language processing at the University of Osnabrück in Germany, says this research could make neural networks more-efficient learners. This would reduce the gargantuan amount of data necessary to train systems such as ChatGPT and would minimize ‘hallucination’,which occurs when AI perceives patterns that are non-existent and creates inaccurate outputs.“Infusing systematicity into neural networks is a big deal,” Bruni says. “It could tackle both these issues at the same time.”
doi: https://doi.org/10.1038/d41586-023-03272-3
References
Lake, B. M. & Baroni, M. Nature https://doi.org/10.1038/s41586-023-06668-3 (2023).
***
http://keskustelu.skepsis.fi/Message/FlatMessageIndex/410525?page=1#410533
" Risto Koivula
18.10.2023 06:14:03
410533
Ämmät kaakattaa tyhjää asiasta, josta eivät ymmärrä enenpää kuin siat Pohjantähdestä.
Ei ollenkaan sen puoleen, että minä ymmärtäisin. Ennen muinoin ohjelmistokehi-tyksen idea oli,että hommat,jotka siihen asti on tehty älyä käyttäen, voidaankin tietokoneen avulla tehdä siten,että se EI VAADIKAAN ÄLYÄ:koneelta ollenkaan ja käyttäjältäkin selvästi vähemmän kuin ennen. Jos aivan välttämättä tarvitaan älyä vaativia ratkaisuja, kone kysyy niitä päätöksiä sopivissa kohdissa. Se mikä on tullut uutta on laskenteho ja koneiden ja käyttäjien verkostoituminen.
Noita tasa-arvolatteuksia voidaan liittää tasan yhtä hyvin tai huonosti mihin alaan tahansa: esimerkiksi Halonen saattaisi vaatia, että "piikojen on levitettävä yhtä paljon sontaa kuin renkienkin".Sellaisista asiaan liittymättömistä säännöistä on yleensä sitä enemmän vahinkoa, mitä pienipiirteisemmälle tasolle ne vedetään - ja mitä tärkeämpiä asioita epäolenniset vaatimukset koskevat.
https://puheenvuoro.uusisuomi.fi/annalahtinen/tekoaly-ja-kestava-kehitys-yrityksissa-yhteiskirjoitus-tarja-halosen-kanssa/
Tekoäly ja kestävä kehitys yrityksissä – yhteiskirjoitus Tarja Halosen kanssa

Anna Lahtinen
16.10.2023 12:00

Tarja Halonen (wittu mikä haaska)
Yritykset ovat avainasemassa kestävän kehityksen ja tekoälyn integroinnissa liiketoi-mintaan ja yhteiskuntaan.Yritysten on tärkeää ymmärtää kestävän kehityksen merki- tys, sen tarjoamat mahdollisuudet ja niihin liittyvät haasteet, sekä rohkeasti omaksua tekoäly. YK:n Agenda 2030 kestävän kehityksen tavoitteet edellyttävät laajaa yhteis-työtä eri toimijoiden,kuten yritysten,korkeakoulujen,julkisen sektorin organisaatioiden kesken.Liiketoiminta- ja markkinamahdollisuuksien tunnistaminen näissä tavoitteissa vaatii yrityksiltä oma-aloitteisuutta, ekosysteemiajattelua ja yhteistyökykyä.
Tekoälyllä on potentiaali tukea sellaisten järjestelmien kehittämisessä, jotka kunnioit-tavat ihmisoikeuksia, edistävät tasa-arvoa ja demokratiaa sekä tukevat kansallista ja kansainvälistä kehitystä.Digitaalisen transformaation ja kestävän kehityksen yhdistä- minen on haasteellista, mutta suomalaisyrityksillä on tarvittavat valmiudet vastata tähän haasteeseen.
Tasa-arvo tekoälyn käyttöönotossa
Tekoälyn käyttöönotossa tasa-arvo on olennainen tekijä. Sukupuolten epätasapaino teknisissä ammateissa ja tekoälyn koulutuksessa heijastaa laajempia yhteiskunnalli-sia tasa-arvo-haasteita. Yrityksiä ja koulutusjärjestelmiä tulisi rohkaista kannusta-maan tyttöjä ja naisia teknologia-alalle. Teknologian ja tekoälyn kehittämisessä on tärkeää ottaa huomioon myös muut väestöryhmät, kuten vähemmistökieliset, maahanmuuttajat ja eri kulttuuritaustoista tulevat ihmiset.
Tulevaisuuden osaamistarpeet ja digitaalinen työympäristö
Suomi kohtaa monitasoisia haasteita tulevaisuuden työvoiman ja osaamisen suh-teen. Yhteiskunnan tulee tarkastella näitä haasteita kokonaisvaltaisesti ja määrittää painopistealueet. Kolmikantainen yhteistyömalli (työnantajat, työntekijät, valtio) on osoittautunut toimivaksi, mutta sen jatkuvaa kehittämistä tarvitaan. "
RK:Kolmikanta on nostanut "johtajiksi" miljoonapalkoiille tuhotöistä esimerkiksi meitä tieteentekiojöitä terrorisoimaan täysin mistään mitääntietämättömiä "lauripyllyjäkin"...
" Yrityksiä tulisi kannustaa hyödyntämään tekoälyn sovellusmahdollisuuksia, sillä tie-tämättömyys ja ymmärtämättömyys ovat merkittävimmät esteet sen käytölle. Tiedon laatu on tärkeää kaikissa järjestelmissä, tekoälyn sovelluksia unohtamatta. Tekoälyn soveltamiseen liittyy myös eettisiä kysymyksiä, joissa demokratian rooli korostuu. Tulevaisuuden työelämässä vastuullisuus, tasa-arvo ja eettisyys nousevat yhä tärkeämmiksi tekijöiksi.
”Yritysten pitäisi ehdottomasti tutustua kestävään kehitykseen, sen antamiin mahdol-lisuuksiin ja haasteisiin sekä myös tekoälyyn. Olin mukana koko tämän vuosituhan-nen YK:n Agenda2030 kestävän kehityksen tavoitteiden asettelussa. Alun alkujaan-kin pidettiin aika utopistisena ajatusta,että me pystyisimme kehittämään järjestelmän ,jonka pohja on ihminen ja ihmisen ymmärrys luontoon,ihmisoikeuksiin, tasa-arvoon, demokratiaan ja olla vielä samanaikaisesti kykeneviä sekä kansalliseen että kansainväliseen kehitykseen. Siinä oli niin monta tuntematonta tekijää, ja minun oma mielenkiintoni on ollut siinä, että pystytäänkö tekoälyn ja muiden uusien teknologioiden keinoin täyttämään nämä aukkokohdat.”
– Presidentti Tarja Halonen
Blogikirjoitus on osa Haaga-Helian Tekoäly Suomessa -haastattelusarjaa, johon kuu-luu myös YouTube-videosarja. Haaga-Helia ammattikorkeakoulun toteuttama sarja on osa ”Tekoälyinnovaatioekosysteemillä kilpailukykyä PK-yrityksille Etelä-Suomes-sa” eli AI-TIE Etelä-Suomi -hanketta. AI-TIE:tä ovat tukeneet Euroopan aluekehitys-rahasto sekä Uudenmaan ja Kymenlaakson liitot osana Euroopan unionin Covid-19-pandemian johdosta toteuttamia toimia.
***
https://puheenvuoro.uusisuomi.fi/teuvomoisa/chatgbt-neuvoo-kuinka-paasee-alkuun-pahojen-henkien-karkoittamisessa/
" ChatGBT neuvoo, kuinka pääsee alkuun pahojen henkien karkoittamisessa

Teuvo Moisa 5.12.2023 0:06
Heti alkuun totean,että maailmankuvani on naturalistinen.En siis usko minkäänlaisen henkimaailman olemassaoloon.
Tässä ChatGBT:n ohjeet manaajaksi haluaville:
Pahan henkien karkottamisen opiskeluun liittyy monia eri näkökulmia ja perinteitä, riippuen kulttuurista ja uskonnollisesta taustasta.Tässä on muutamia yleisiä vaiheita, jotka voivat auttaa aloittamaan:
- Tutustu eri kulttuurien ja uskontojen näkemyksiin:Pahojen henkien karkottaminen on osa monia uskontoja ja kulttuureja, mukaan lukien kristinusko, islam, hindulai-suus ja erilaiset shamanistiset perinteet. Lue kirjallisuutta ja tutki näitä eri perinteitä.
- Opiskele uskontoa tai henkistä polkua: Usein pahojen henkien karkottamiseen liittyvät rituaalit ovat osa laajempaa uskonnollista tai henkistä käytäntöä. Tutustuminen tähän taustaan voi olla tärkeää.
- Etsi ohjausta ja mentorointia: Monissa perinteissä pahan henkien karkottamisen taitoja opetetaan suoraan mentorin tai kokeneemman henkilön ohjauksessa. Etsi henkilöä, joka on kokenut näissä käytännöissä.
- Harjoittele henkistä itsepuolustusta ja suojausta: Ennen kuin alat työskennellä pahojen henkien kanssa, on tärkeää oppia suojaamaan itsesi henkisesti ja energisesti.
- Osallistu kursseille tai työpajoihin: Joissakin tapauksissa voi olla saatavilla kursseja tai työpajoja, jotka keskittyvät pahojen henkien karkottamiseen.
- Ole varovainen ja kriittinen: On tärkeää lähestyä tätä aihetta varoen ja kriittisesti. Ei kaikki mikä väittää olevansa pahan henkien karkotusta, välttämättä ole turvallista tai eettistä.
- Henkilökohtainen kehitys ja itsetuntemus: Henkisten käytäntöjen syvempi ymmärtäminen vaatii usein henkilökohtaista kehitystä ja itsetuntemusta.
Muista, että pahojen henkien karkottaminen voi olla henkisesti ja emotionaalisesti vaativaa, ja se ei sovi kaikille. On myös tärkeää tunnistaa, että eri kulttuureilla ja uskonnoilla on omat ainutlaatuiset käytäntönsä ja uskomuksensa, jotka tulee kunnioittaa.
***
https://www.tekniikkatalous.fi/uutiset/karut-luvut-41-johtajista-uskoo-tekoalyn-vahentavan-tyopaikkoja-vain-muutamassa-vuodessa/a36c6d0c-bbd8-4494-9ef3-075012e8110d
" Tekoäly
Karut luvut: 41 johtajista uskoo tekoälyn vähentävän työpaikkoja vain muutamassa vuodessa
Johtoportaassa on herännyt nälkä henkilöstön korvaamiseksi tekoälyillä.

Tekoäly tulee. Hurjan nosteen ja hypen myötä tekoälytoiveista on muodostunut odotuksia.
Tekoälyn mahdollisuudet tuntuvat monista rajattomilta. Tekoälyn käyttöönoton uskotaan mullistavan teollista maailmaa merkittävästi, kenties ennennäkemättömästi. Monet uskovat tekoälyn kykenevän pian hoitamaan rutiininomaisia tehtäviä ilman ihmisen opastusta.
Koska kapitalistinen yhteiskunta keskittyy maksimoimaan voittoa eikä tuomaan ihmisille lisää vapaa-aikaa , on työtätekevien keskuudessa vallalla aiheellinen pelko siitä, että tekoäly korvaa heidät ja passittaa heidät kilometritehtaalle.
The Register kertoo, että työvoima- ja rekrytointitoimisto Adecco Group teetätti tutki-muksen, jossa se tiedusteli 2000 suuren yhtiön johtajilta yhdeksässä maassa heidän mielipiteitään tekoälyn mahdollisuuksista.
Tulokset ovat karua luettavaa. Sen mukaan vain noin puolet yrityksistä,46 prosenttia, aikoo järjestää uuden työnkuvan niille ihmisille, joiden työt tekoäly vie.
Johtajista 41 prosenttia uskoo, että tekoälyn ansiosta heidän yhtiönsä työllistää vähemmän ihmisiä viidessä vuodessa. Vakavin tilanne on Saksassa ja Ranskassa, joissa 49 prosenttia vastanneista uskoo näin. Singaporessa vain 32 prosenttia johtajista on tullut tähän johtopäätökseen, ja Yhdysvalloissa luku on 36 %.
Suomalaisia johtajia kyselyyn ei osallistunut, joten Adeccon tutkimus ei paljasta kotimaista nälkää.Yhtiöillä on myös halu ostaa osaamista sen sijaan, että osaajia koulutettaisiin itse. Adeccon mukaan tämä saattaa pahentaa osaajapulaa ja luoda kaksivaiheisen työpaikkakulttuurin.
Tutkimuksen mukaan tilanne ei ole ihmisten kannalta täysi katastrofi. 78 prosenttia vastanneista johtajista uskoo, että generatiivinen tekoäly tulee näyttelemään kriittistä roolia työntekijöiden kykyjen kehittämisessä.
LUE MYÖS
***
https://en.isna.ir/news/1403101309562/Putin-calls-for-AI-alliance-with-China
Putin calls for AI alliance with China
Russian President Vladimir Putin has instructed the government and Sberbank, the country’s largest bank and a tech innovator, to team up with China to further develop artificial intelligence.
Tehran - ISNA - The directive, issued after an AI-themed conference in December, tasks Prime Minister Mikhail Mishustin and Sberbank CEO Herman Gref with spearheading the initiative. A progress report is expected by April 2025.
The partnership aims to tap into China’s AI expertise, which is recognized as being among the world’s most advanced. Sberbank, a leader in developing AI in Russia, has looked to China as a key inspiration for many of its projects. Alexander Vedyakhin, the bank’s first deputy chairman, recently credited China’s AI breakthroughs with shaping Sberbank’s own ambitions.
China has heavily invested in AI, aiming to become the global leader by 2030, according to its ‘New Generation Artificial Intelligence Development Plan’ launched in 2017. Beijing has rapidly implemented AI across various sectors, including manufacturing, healthcare, and transportation, and leads in AI patent applications, particularly in generative AI technologies. Between 2014 and 2023, Chinese entities filed over 38,000 generative AI patents, accounting for approximately 70% of such filings worldwide.
Chinese researchers have significantly increased their contributions to AI literature. China surpassed the US in terms of total number of AI-related journal citations already in 2020.
During the December conference, Putin also emphasized the need to increase efforts to develop AI domestically. He’s called for expanded AI use in schools to improve student counseling and learning, as well as support for local governments to integrate AI into public administration.
The Russian president announced that AI had helped slash robberies by 10.5 times and home burglaries by 34.5 times. In December 2024, the country introduced its first AI textbooks for students in grades 5-9. These textbooks provide an introduction to AI, detailing how it works, how specialists interact with it, and how it is applied across various industries. “Russia must become a world leader not only in terms of creating, but also adopting and integrating artificial intelligence in all spheres of our life without exception,” he said. "
***
https://scitechdaily.com/are-machines-truly-thinking-modern-ai-systems-have-finally-achieved-turings-vision/
" Technology
Are Machines Truly Thinking? Modern AI Systems Have Finally Achieved Turing’s Vision
By Intelligent Computing January 10, 2025

Modern AI systems have fulfilled Turing’s vision of machines that learn and converse like humans, but challenges remain. A new paper highlights concerns about energy consumption and societal inequality while calling for more robust AI testing to ensure ethical and sustainable progress.
A perspective published on November 13 in Intelligent Computing, a Science Partner Journal, argues that modern artificial intelligence systems have fulfilled Alan Turing’s decades-old vision: machines capable of learning from experience and engaging in human-like conversations. Authored by Bernardo Gonçalves, a researcher affiliated with the University of São Paulo and the University of Cambridge, the paper exami-nes the alignment between contemporary AI technologies and Turing’s ideas, while highlighting key differences.
The paper emphasizes how today’s transformer-based systems - despite their significant energy demands - contrast with Turing’s concept of machines developing intelligence naturally, akin to the learning process of human children. Gonçalves notes that transformers,which power current generative AI models,provide what Turing described as “adequate proof” of machine intelligence. Leveraging attention mechanisms and large-scale learning, these systems now excel in tasks traditionally associated with human cognition, such as generating coherent text, solving complex problems, and engaging in discussions about abstract concepts.
The Evolution of AI and Turing’s Influence
“Without resorting to preprogramming or special tricks, their intelligence grows as they learn from experience, and to ordinary people, they can appear human-like in conversation,” writes Gonçalves. “This means that they can pass the Turing test and that we are now living in one of many possible Turing futures where machines can pass for what they are not.”

Modern AI systems have fulfilled Alan Turing’s vision by learning from experience and passing the Turing Test. However, a recent paper stresses their divergence from Turing’s ideal of energy-efficient, naturally developing intelligence, raising concerns about sustainability and societal inequality. It calls for rigorous, Turing-inspired testing to guide future AI development ethically.
This achievement traces back to Turing’s 1950 concept of the “imitation game,” in which a machine would attempt to mimic a human in a remote conversation, decei-ving a non-expert judge. The test became a cornerstone of artificial intelligence re-search,with early AI pioneers John McCarthy and Claude Shannon considering it the “Turing definition of thinking” and Turing’s “strong criterion.” Popular culture, too, un-deniably reflects Turing’s influence: the HAL-9000 computer in the Stanley Kubrick film 2001: A Space Odyssey famously passed the Turing test with ease.
However, the paper underscores that Turing’s ultimate goal was not simply to create machines that could trick humans into thinking they were intelligent.Instead, he envi-sioned “child machines” modeled on the natural development of the human brain — systems that would grow and learn over time, ultimately becoming powerful enough to have a meaningful impact on society and the natural world.
Challenges in Modern AI Development
The paper highlights concerns about current AI development.While Turing advocated for energy-efficient systems inspired by the natural development of the human brain, today’s AI systems consume massive amounts of computing power, raising sustain-ability concerns. Additionally, the paper draws attention to Turing’s ahead-of-his-time societal warnings. He cautioned that automation should affect all levels of society equally, not just displace lower-wage workers while benefiting only a small group of technology owners - an issue that resonates strongly with current debates about AI’s impact on employment and social inequality.
Looking ahead,the paper calls for Turing-like AI testing that would introduce machine adversaries and statistical protocols to address emerging challenges such as data contamination and poisoning.These more rigorous evaluation methods will ensure AI systems are tested in ways that reflect real-world complexities, aligning with Turing’s vision of sustainable and ethically guided machine intelligence.
Reference:“Passed the Turing Test:Living in Turing Futures” by Bernardo Gonçalves, 13 November 2024, Intelligent Computing.
DOI: 10.34133/icomputing.0102 "
,,,
WITUT NE KONEET IKINÄ MITÄÄN YMMÄRTÄÄ HELVETIN ÄÄLIÖ!!!
https://puheenvuoro.uusisuomi.fi/riikka-tanner/missa-olit-silloin-kun-tekoaly-alkoi-ymmartaa/
Missä olit silloin, kun tekoäly alkoi ymmärtää?
" Riikka Tanner
06.04.2025 08:20
Tätä tekstiä kirjoitetaan vuonna 2030. Se on fiktiivinen näkymä vuosien 2025–2027 murrosvaiheeseen: aikaan, jolloin teknolo-gia eteni nopeammin kuin työmarkkinat, koulutusjärjestelmä ja päätöksenteko ehtivät reagoida.
Kuka muistaa vielä vuoden 2025? Se oli se vuosi, kun tekoäly otti askeleen lähemmäs ihmistä. Me sen sijaan emme ymmärtäneet vielä hetkeen, mitä se tulisi tarkoittamaan.
En nyt tarkoita sitä, miten kielimallit oppivat tuottamaan (lähes) virheettömiä vastauksia tai somesisältöä, vaan sitä vaivihkaan tapahtunutta muutosta, kun koneet alkoivat ymmärtää tarkoitusperiämme. Konteksteja. Painotuksia. Kun ne alkoivat osallistua keskusteluun.
Roaring 20s osoittautui juuri sellaiseksi kuin edeltäjänsä sata vuotta aikaisemmin. Talouskasvun ja jazz-sointujen sijaan saimme yhteiskunnallisen murroksen, geopoliittisesti räjähdysherkän, äänekkään, monella tapaa vallankumouksellisen vuosikymmenen.
Suomessa puhutaan mielellään tasa-arvosta, mutta teknologinen murros on harvoin tasa-arvoinen. Vuodet 2025–2027 loivat kuilun niiden välille, jotka ottivat nopeasti uuden teknologian haltuun ja niiden, jotka jäivät lähtötelineisiin. Erityisesti pk-sek-torilla siirtymä ei ollut tasaista. Osa yrityksistä oli jo liikkeellä, toisten arastellessa, odottaessa.
Mutta juuri siinä odottamisessa menetettiin aikaa, jota ei ollut. Tekoäly kehittyi eks-ponentiaalisesti, mutta ihmisten kyky uudelleenorientoitua ei ollut samalla tasolla. Se, mikä yllätti monet, oli se miten nopeasti työtehtävät,joita oli pidetty inhimillisinä vahvuuksina siirtyivät nekin koneiden tehtäväksi.
Työpaikat eivät kadonneet kerralla,vaan ne muuttuivat yksi kerrallaan tarpeettomik-si. Ei tullut mitään massairtisanomisten aaltoa, mutta lähteneiden ja eläköityneiden tilalle ei enää palkattu uusia.Sitä seurasi ennennäkemätön rakenteellinen työttömyys , josta ei voinut syyttää taantumaa vaan muutoskyvyttömyyttä, oikeastaan vähän kaikilla tasoilla.
Ei löytynyt riittävän ajoissa työkaluja, taitoja ja rakenteita tukemaan valtavassa uu-delleenkouluttautumisen tarpeessa.Työmarkkinat olivat läpikäyneet ison muutoksen , mutta asenteet muuttuivat hitaasti. Ristiriitaiset viestit täyttivät uutismedian.
Samaan aikaan markkinoilla nähtiin brutaalia kilpailua katoavista työpaikoista, kun toisaalla kärsittiin työvoimapulasta. Kauppasodat olivat nekin jättäneet jälkensä maailmantalouteen, ja sitä laskua maksettaisiin vielä pitkään.
Oppilaitokset yrittivät reagoida, mutta hidas reagointikyky, raskaat opetussuunnitel-mat ja henkilökunnan vaihteleva osaaminen estivät laajamittaisen vastauksen. Kun tekoälyn murros vyöryi läpi työelämän, suuri osa oppilaitoksista oli vielä vaiheessa, jossa keskusteltiin tekoälyn käytön sallimisesta, ei sen ymmärtämisestä työkaluna.
Muistelin hetki sitten Johdon agendalla podcast jaksoa, jossa juttelimme OP-ryhmän pääjohtajan Timo Ritakallion kanssa tekoälystä ja muutoskyvykkyydestä. Se oli kevättä 2025. Puhuimme silloin luonnollisen kielen kehityksestä ja siitä, miten se tulisi mullistamaan finanssialaa. Näin jälkikäteen ajateltuna elimme melko merkittäviä hetkiä.
Missä sinä olit, kun tämä kaikki alkoi?
🎧 Kuuntele podcast haastattelu esimerkiksi Youtubessa tai Spotifyssa. "
HEWOWWITTUA!!!
Kommentit