{"id":12519,"date":"2024-05-22T18:16:07","date_gmt":"2024-05-22T18:16:07","guid":{"rendered":"https:\/\/dailyai.com\/?p=12519"},"modified":"2024-05-24T10:16:44","modified_gmt":"2024-05-24T10:16:44","slug":"decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box","status":"publish","type":"post","link":"https:\/\/dailyai.com\/nl\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/","title":{"rendered":"De AI-geest ontcijferen: Antropische onderzoekers kijken in de \"zwarte doos\""},"content":{"rendered":"<p><b><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span> onderzoekers hebben met succes miljoenen concepten ge\u00efdentificeerd binnen <span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Claude<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span> Sonnet, een van hun gevorderde LLM's.<\/b><\/p>\n<p><span style=\"font-weight: 400;\">AI-modellen worden vaak beschouwd als zwarte dozen, wat betekent dat je er niet in kunt 'kijken' om precies te begrijpen hoe ze werken.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Als je een LLM een invoer geeft, genereert deze een antwoord, maar de redenering achter de keuzes is niet duidelijk. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Je input gaat erin en de output komt eruit - en zelfs de AI-ontwikkelaars zelf begrijpen niet echt wat er in die 'doos' gebeurt.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Neurale netwerken cre\u00ebren hun eigen interne representaties van informatie wanneer ze inputs toewijzen aan outputs tijdens het trainen van gegevens.\u00a0<\/span><span style=\"font-weight: 400;\">De bouwstenen van dit proces, \"neuronactivaties\" genoemd, worden weergegeven door numerieke waarden. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Elk concept is verdeeld over meerdere neuronen en elk neuron draagt bij aan de representatie van meerdere concepten, waardoor het lastig is om concepten direct in kaart te brengen bij individuele neuronen.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Dit is in grote lijnen vergelijkbaar met onze menselijke hersenen. Net zoals onze hersenen zintuiglijke input verwerken en gedachten, gedrag en herinneringen genereren, blijven de miljarden, zelfs triljarden processen achter deze functies voornamelijk onbekend voor de wetenschap.<\/span><\/p>\n<p><a href=\"https:\/\/www.anthropic.com\/research\/mapping-mind-language-model\"><span style=\"font-weight: 400;\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span>onderzoek<\/span><\/a><span style=\"font-weight: 400;\"> probeert in de zwarte doos van AI te kijken met een techniek die \"woordenboekleren\" wordt genoemd.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Dit houdt in dat complexe patronen in een AI-model worden ontleed in lineaire bouwstenen of \"atomen\" die intu\u00eftief zinvol zijn voor mensen.<\/span><\/p>\n<h2>LLM's in kaart brengen met woordenboekleren<\/h2>\n<p><span style=\"font-weight: 400;\">In oktober 2023, <span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span> pasten deze methode toe op een klein \"speelgoed\" taalmodel en vonden coherente kenmerken die overeenkomen met concepten als hoofdletters, DNA-sequenties, achternamen in citaten, wiskundige zelfstandige naamwoorden of functieargumenten in Python-code.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">In dit nieuwste onderzoek wordt de techniek opgeschaald om te werken voor de grotere AI-taalmodellen van vandaag, in dit geval, <span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span>'s <span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Claude<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span> 3 Sonnet.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Hier wordt stap voor stap uitgelegd hoe het onderzoek in zijn werk ging:<\/span><\/p>\n<h4><b>Patronen identificeren met woordenboekleren<\/b><\/h4>\n<p><span style=\"font-weight: 400;\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span> gebruikten woordenboekleren om neuronactivaties in verschillende contexten te analyseren en gemeenschappelijke patronen te identificeren. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Woordenboek leren groepeert deze activeringen in een kleinere set van betekenisvolle \"kenmerken\", die concepten van een hoger niveau vertegenwoordigen die door het model zijn geleerd. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Door deze kenmerken te identificeren, kunnen onderzoekers beter begrijpen hoe het model informatie verwerkt en weergeeft.<\/span><\/p>\n<h4><b>Kenmerken extraheren uit de middelste laag<\/b><\/h4>\n<p><span style=\"font-weight: 400;\">De onderzoekers richtten zich op de middelste laag van <span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Claude<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span> 3.0 Sonnet, dat dient als kritisch punt in de verwerkingspijplijn van het model. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Door woordenboekleren toe te passen op deze laag worden miljoenen kenmerken ge\u00ebxtraheerd die de interne representaties en geleerde concepten van het model in dit stadium vastleggen. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Door kenmerken uit de middelste laag te extraheren, kunnen onderzoekers onderzoeken hoe het model informatie begrijpt. <em>na<\/em> het heeft de invoer verwerkt <em>voor<\/em> die de uiteindelijke uitvoer genereert.<\/span><\/p>\n<h4><b>Diverse en abstracte concepten ontdekken<\/b><\/h4>\n<p><span style=\"font-weight: 400;\">De ge\u00ebxtraheerde kenmerken onthulden een uitgebreide reeks concepten die geleerd waren door <span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Claude<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span>Van concrete entiteiten zoals steden en mensen tot abstracte begrippen gerelateerd aan wetenschappelijke velden en programmeersyntaxis. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Interessant genoeg bleken de kenmerken multimodaal te zijn en te reageren op zowel tekstuele als visuele input, wat aangeeft dat het model concepten kan leren en representeren in verschillende modaliteiten. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Bovendien suggereren de meertalige kenmerken dat het model concepten in verschillende talen kan begrijpen.<\/span><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"598\" class=\"wp-image-12521 size-large\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/c896a301ad3d1ef4237cb05b68d78b467c444097-2200x1284-1-1024x598.webp\" alt=\"&lt;span class=\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/c896a301ad3d1ef4237cb05b68d78b467c444097-2200x1284-1-1024x598.webp 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/c896a301ad3d1ef4237cb05b68d78b467c444097-2200x1284-1-300x175.webp 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/c896a301ad3d1ef4237cb05b68d78b467c444097-2200x1284-1-768x448.webp 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/c896a301ad3d1ef4237cb05b68d78b467c444097-2200x1284-1-1536x896.webp 1536w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/c896a301ad3d1ef4237cb05b68d78b467c444097-2200x1284-1-2048x1195.webp 2048w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/c896a301ad3d1ef4237cb05b68d78b467c444097-2200x1284-1-18x12.webp 18w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/c896a301ad3d1ef4237cb05b68d78b467c444097-2200x1284-1-60x35.webp 60w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/p>\n<h3><b>De organisatie van concepten analyseren<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Om te begrijpen hoe het model verschillende concepten organiseert en met elkaar in verband brengt, analyseerden de onderzoekers de overeenkomsten tussen kenmerken op basis van hun activeringspatronen. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Ze ontdekten dat kenmerken die verwante concepten vertegenwoordigen de neiging hadden om samen te clusteren. Kenmerken die bijvoorbeeld geassocieerd werden met steden of wetenschappelijke disciplines vertoonden een grotere overeenkomst dan kenmerken die niet-gerelateerde concepten vertegenwoordigden. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Dit suggereert dat de interne organisatie van concepten in het model tot op zekere hoogte overeenkomt met menselijke intu\u00efties over conceptuele relaties.<\/span><\/p>\n<figure id=\"attachment_12520\" aria-describedby=\"caption-attachment-12520\" style=\"width: 1024px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-12520 size-large\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/fe4d42c004bf43efda0f5921adfedd2f8f42e417-2200x2140-1-1024x996.webp\" alt=\"antropisch\" width=\"1024\" height=\"996\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/fe4d42c004bf43efda0f5921adfedd2f8f42e417-2200x2140-1-1024x996.webp 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/fe4d42c004bf43efda0f5921adfedd2f8f42e417-2200x2140-1-300x292.webp 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/fe4d42c004bf43efda0f5921adfedd2f8f42e417-2200x2140-1-768x747.webp 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/fe4d42c004bf43efda0f5921adfedd2f8f42e417-2200x2140-1-1536x1494.webp 1536w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/fe4d42c004bf43efda0f5921adfedd2f8f42e417-2200x2140-1-2048x1992.webp 2048w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/fe4d42c004bf43efda0f5921adfedd2f8f42e417-2200x2140-1-12x12.webp 12w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/fe4d42c004bf43efda0f5921adfedd2f8f42e417-2200x2140-1-60x58.webp 60w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/fe4d42c004bf43efda0f5921adfedd2f8f42e417-2200x2140-1-24x24.webp 24w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/fe4d42c004bf43efda0f5921adfedd2f8f42e417-2200x2140-1-48x48.webp 48w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption id=\"caption-attachment-12520\" class=\"wp-caption-text\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span> abstracte begrippen als \"innerlijk conflict\" in kaart wist te brengen. Bron: <a href=\"https:\/\/www.anthropic.com\/research\/mapping-mind-language-model\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/a>.<\/figcaption><\/figure>\n<h4><b>De functies controleren<\/b><\/h4>\n<p><span style=\"font-weight: 400;\">Om te bevestigen dat de ge\u00efdentificeerde kenmerken het gedrag en de uitvoer van het model direct be\u00efnvloeden, voerden de onderzoekers experimenten uit met \"kenmerksturing\". <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Dit bestond uit het selectief versterken of onderdrukken van de activatie van specifieke kenmerken tijdens de verwerking van het model en het observeren van het effect op de reacties. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Door individuele kenmerken te manipuleren, konden onderzoekers een direct verband leggen tussen individuele kenmerken en het gedrag van het model. Door bijvoorbeeld een kenmerk met betrekking tot een bepaalde stad te versterken, genereerde het model stadsafhankelijke uitkomsten, zelfs in irrelevante contexten.<\/span><\/p>\n<p>Lees het volledige onderzoek <a href=\"https:\/\/transformer-circuits.pub\/2024\/scaling-monosemanticity\/index.html\" target=\"_blank\" rel=\"noopener\">hier<\/a>.<\/p>\n<p><iframe loading=\"lazy\" title=\"Woordenboek leren over Claude 3 Sonnet\" width=\"1080\" height=\"608\" src=\"https:\/\/www.youtube.com\/embed\/CJIbCV92d88?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/p>\n<h2>Waarom interpreteerbaarheid cruciaal is voor AI-veiligheid<\/h2>\n<p><span style=\"font-weight: 400;\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span>Het onderzoek is fundamenteel relevant voor de interpreteerbaarheid van AI en, in het verlengde daarvan, veiligheid.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Inzicht in hoe LLM's informatie verwerken en weergeven, helpt onderzoekers om risico's te begrijpen en te beperken. Het <\/span><span style=\"font-weight: 400;\">legt de basis voor de ontwikkeling van transparantere en beter verklaarbare AI-systemen.\u00a0<\/span><\/p>\n<p>Als <span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span> legt uit: \"We hopen dat wij en anderen deze ontdekkingen kunnen gebruiken om modellen veiliger te maken. Het zou bijvoorbeeld mogelijk kunnen zijn om de hier beschreven technieken te gebruiken om AI-systemen te controleren op bepaald gevaarlijk gedrag (zoals het misleiden van de gebruiker), om ze in de richting van gewenste uitkomsten te sturen (debiasing), of om bepaalde gevaarlijke onderwerpen helemaal te verwijderen.\"<\/p>\n<p><span style=\"font-weight: 400;\">Het ontsluiten van een beter begrip van AI-gedrag wordt van het grootste belang naarmate ze alomtegenwoordig worden voor kritieke besluitvormingsprocessen op gebieden als gezondheidszorg, financi\u00ebn en strafrecht. Het helpt ook om de hoofdoorzaak van <a href=\"https:\/\/dailyai.com\/nl\/2023\/06\/anthropic-releases-paper-highlighting-the-potential-bias-of-large-language-models\/\">bias<\/a>hallucinaties en ander ongewenst of onvoorspelbaar gedrag.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Bijvoorbeeld een <\/span><a href=\"https:\/\/dailyai.com\/nl\/2024\/01\/researchers-aim-to-determine-how-black-box-drug-discovery-models-work\/\"><span style=\"font-weight: 400;\">recente studie<\/span><\/a><span style=\"font-weight: 400;\"> van de Universiteit van Bonn ontdekte hoe grafische neurale netwerken (GNN's) die worden gebruikt voor het ontdekken van medicijnen, sterk vertrouwen op het oproepen van overeenkomsten uit trainingsgegevens in plaats van het echt leren van complexe nieuwe chemische interacties. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Dit maakt het moeilijk om te begrijpen hoe deze modellen precies nieuwe interessante verbindingen bepalen.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Vorig jaar was de <\/span><a href=\"https:\/\/dailyai.com\/nl\/2023\/09\/the-uk-government-wants-to-see-inside-ais-black-box\/\"><span style=\"font-weight: 400;\">Britse overheid onderhandeld<\/span><\/a><span style=\"font-weight: 400;\"> met grote techgiganten zoals <span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">OpenAI<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span> en <span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">DeepMind<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span>die toegang willen tot de interne besluitvormingsprocessen van hun AI-systemen.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Regelgeving zoals de <a href=\"https:\/\/dailyai.com\/nl\/2024\/03\/the-eu-ai-act-passed-in-a-landslide-and-will-come-into-force-this-year\/\">AI-wet van de EU<\/a> zal AI-bedrijven onder druk zetten om transparanter te worden, hoewel commerci\u00eble geheimen achter slot en grendel lijken te blijven.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span>Het onderzoek biedt een glimp van wat er in de doos zit door informatie over het model 'in kaart te brengen'.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">De waarheid is echter dat deze modellen zo uitgebreid zijn dat, door <span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\"><span class=\"noTranslate\" data-no-translation=\"\">Anthropic<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/span>\"We denken dat het heel waarschijnlijk is dat we ordes van grootte te kort komen en dat als we alle kenmerken zouden willen krijgen - in alle lagen! - we veel meer rekenkracht nodig zouden hebben dan de totale rekenkracht die nodig is om de onderliggende modellen te trainen.\"<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Dat is een interessant punt - het reverse engineeren van een model is rekenkundig complexer dan het engineeren van het model zelf.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Het doet denken aan enorm dure neurowetenschapsprojecten zoals de <a href=\"https:\/\/dailyai.com\/nl\/2023\/08\/exploring-impact-of-the-human-brain-project-hbp-on-science-and-ai\/\">Human Brain Project (HBP)<\/a>die miljarden heeft gestoken in het in kaart brengen van onze eigen menselijke hersenen om uiteindelijk te falen.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Onderschat nooit hoeveel er in de zwarte doos zit.\u00a0<\/span><\/p>","protected":false},"excerpt":{"rendered":"<p>Antropische onderzoekers hebben met succes miljoenen concepten ge\u00efdentificeerd in Claude Sonnet, een van hun geavanceerde LLM's. AI-modellen worden vaak beschouwd als zwarte dozen, wat betekent dat je er niet in kunt 'kijken' om te begrijpen hoe ze precies werken.  Wanneer je een LLM een input geeft, genereert het een antwoord, maar de redenering achter zijn keuzes is niet duidelijk. Je input gaat erin en de output komt eruit - en zelfs de AI-ontwikkelaars zelf begrijpen niet echt wat er in die 'doos' gebeurt.  Neurale netwerken cre\u00ebren hun eigen interne representaties van informatie wanneer ze inputs toewijzen aan outputs tijdens het trainen van gegevens. De bouwstenen van deze<\/p>","protected":false},"author":2,"featured_media":12522,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[148,105],"class_list":["post-12519","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-anthropic","tag-machine-learning"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Decoding the AI mind: Anthropic researchers peer inside the &quot;black box&quot; | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/nl\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/\" \/>\n<meta property=\"og:locale\" content=\"nl_NL\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Decoding the AI mind: Anthropic researchers peer inside the &quot;black box&quot; | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Anthropic researchers successfully identified millions of concepts within Claude Sonnet, one of their advanced LLMs. AI models are often considered black boxes, meaning you can&#8217;t &#8216;see&#8217; inside them to understand exactly how they work.\u00a0 When you provide an LLM with an input, it generates a response, but the reasoning behind its choices isn\u2019t clear. Your input goes in, and the output comes out \u2013 and even the AI developers themselves don&#8217;t truly understand what happens inside that &#8216;box.&#8217;\u00a0 Neural networks create their own internal representations of information when they map inputs to outputs during data training.\u00a0The building blocks of this\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/nl\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-05-22T18:16:07+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-24T10:16:44+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-22-19.15.50-Anthropic-researchers-studying-artificial-intelligence-inside-a-high-tech-laboratory-with-a-prominent-black-box-in-the-center.-The-scene-features-adva.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1792\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Sam Jeans\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Geschreven door\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Geschatte leestijd\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minuten\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"Decoding the AI mind: Anthropic researchers peer inside the &#8220;black box&#8221;\",\"datePublished\":\"2024-05-22T18:16:07+00:00\",\"dateModified\":\"2024-05-24T10:16:44+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/\"},\"wordCount\":1075,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/DALL\u00b7E-2024-05-22-19.15.50-Anthropic-researchers-studying-artificial-intelligence-inside-a-high-tech-laboratory-with-a-prominent-black-box-in-the-center.-The-scene-features-adva.webp\",\"keywords\":[\"Anthropic\",\"machine learning\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"nl-NL\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/\",\"name\":\"Decoding the AI mind: Anthropic researchers peer inside the \\\"black box\\\" | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/DALL\u00b7E-2024-05-22-19.15.50-Anthropic-researchers-studying-artificial-intelligence-inside-a-high-tech-laboratory-with-a-prominent-black-box-in-the-center.-The-scene-features-adva.webp\",\"datePublished\":\"2024-05-22T18:16:07+00:00\",\"dateModified\":\"2024-05-24T10:16:44+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/#breadcrumb\"},\"inLanguage\":\"nl-NL\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"nl-NL\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/DALL\u00b7E-2024-05-22-19.15.50-Anthropic-researchers-studying-artificial-intelligence-inside-a-high-tech-laboratory-with-a-prominent-black-box-in-the-center.-The-scene-features-adva.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/DALL\u00b7E-2024-05-22-19.15.50-Anthropic-researchers-studying-artificial-intelligence-inside-a-high-tech-laboratory-with-a-prominent-black-box-in-the-center.-The-scene-features-adva.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Decoding the AI mind: Anthropic researchers peer inside the &#8220;black box&#8221;\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"nl-NL\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"nl-NL\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\",\"name\":\"Sam Jeans\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"nl-NL\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"caption\":\"Sam Jeans\"},\"description\":\"Sam is a science and technology writer who has worked in various AI startups. When he\u2019s not writing, he can be found reading medical journals or digging through boxes of vinyl records.\",\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/sam-jeans-6746b9142\\\/\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/nl\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"De AI-geest ontcijferen: Antropische onderzoekers kijken in de \"zwarte doos\" | DailyAI","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/nl\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/","og_locale":"nl_NL","og_type":"article","og_title":"Decoding the AI mind: Anthropic researchers peer inside the \"black box\" | DailyAI","og_description":"Anthropic researchers successfully identified millions of concepts within Claude Sonnet, one of their advanced LLMs. AI models are often considered black boxes, meaning you can&#8217;t &#8216;see&#8217; inside them to understand exactly how they work.\u00a0 When you provide an LLM with an input, it generates a response, but the reasoning behind its choices isn\u2019t clear. Your input goes in, and the output comes out \u2013 and even the AI developers themselves don&#8217;t truly understand what happens inside that &#8216;box.&#8217;\u00a0 Neural networks create their own internal representations of information when they map inputs to outputs during data training.\u00a0The building blocks of this","og_url":"https:\/\/dailyai.com\/nl\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/","og_site_name":"DailyAI","article_published_time":"2024-05-22T18:16:07+00:00","article_modified_time":"2024-05-24T10:16:44+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-22-19.15.50-Anthropic-researchers-studying-artificial-intelligence-inside-a-high-tech-laboratory-with-a-prominent-black-box-in-the-center.-The-scene-features-adva.webp","type":"image\/webp"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Geschreven door":"Sam Jeans","Geschatte leestijd":"6 minuten"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"Decoding the AI mind: Anthropic researchers peer inside the &#8220;black box&#8221;","datePublished":"2024-05-22T18:16:07+00:00","dateModified":"2024-05-24T10:16:44+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/"},"wordCount":1075,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-22-19.15.50-Anthropic-researchers-studying-artificial-intelligence-inside-a-high-tech-laboratory-with-a-prominent-black-box-in-the-center.-The-scene-features-adva.webp","keywords":["Anthropic","machine learning"],"articleSection":["Industry"],"inLanguage":"nl-NL"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/","url":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/","name":"De AI-geest ontcijferen: Antropische onderzoekers kijken in de \"zwarte doos\" | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-22-19.15.50-Anthropic-researchers-studying-artificial-intelligence-inside-a-high-tech-laboratory-with-a-prominent-black-box-in-the-center.-The-scene-features-adva.webp","datePublished":"2024-05-22T18:16:07+00:00","dateModified":"2024-05-24T10:16:44+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/#breadcrumb"},"inLanguage":"nl-NL","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/"]}]},{"@type":"ImageObject","inLanguage":"nl-NL","@id":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-22-19.15.50-Anthropic-researchers-studying-artificial-intelligence-inside-a-high-tech-laboratory-with-a-prominent-black-box-in-the-center.-The-scene-features-adva.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-22-19.15.50-Anthropic-researchers-studying-artificial-intelligence-inside-a-high-tech-laboratory-with-a-prominent-black-box-in-the-center.-The-scene-features-adva.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/05\/decoding-the-ai-mind-anthropic-researchers-peer-inside-the-black-box\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Decoding the AI mind: Anthropic researchers peer inside the &#8220;black box&#8221;"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Uw dagelijkse dosis AI-nieuws","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"nl-NL"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"nl-NL","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9","name":"Sam Jeans","image":{"@type":"ImageObject","inLanguage":"nl-NL","@id":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","caption":"Sam Jeans"},"description":"Sam is een wetenschap- en technologieschrijver die bij verschillende AI-startups heeft gewerkt. Als hij niet aan het schrijven is, leest hij medische tijdschriften of graaft hij door dozen met vinylplaten.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/nl\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/posts\/12519","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/comments?post=12519"}],"version-history":[{"count":11,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/posts\/12519\/revisions"}],"predecessor-version":[{"id":12573,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/posts\/12519\/revisions\/12573"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/media\/12522"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/media?parent=12519"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/categories?post=12519"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/tags?post=12519"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}