De flesta använder ChatGPT för snabba svar. Men enligt dataanalytikern James Wilkins, som skriver i magasinet Data Science Collective, går det att få betydligt mer ut av verktyget. I artikeln ”You’re using ChatGPT wrong – here’s how to prompt like a pro” förklarar han hur forskningsbaserade metoder kan göra svaren både mer korrekta och mer användbara.
Elva forskningsbaserade verktyg som gör dig bättre på ChatGPT
AI De flesta använder ChatGPT för snabba svar. Men enligt dataanalytikern James Wilkins kan genomtänkta prompts ge betydligt bättre resultat. Här är hela listan.

Foto: Adobe Stock
Någonting är fel
Du är inloggad som prenumerant hos förlaget Pauser Media, men nånting är fel. På din profilsida ser du vilka av våra produkter som du har tillgång till. Skulle uppgifterna inte stämma på din profilsida – vänligen kontakta vår kundtjänst.
Kvalitetsmagasinet premium
Läs vidare – starta din prenumeration
Redan prenumerant? Logga in och läs vidare.
Språkmodeller som ChatGPT är i grunden mönsterigenkännare. De förutser vilket ord som sannolikt kommer härnäst, men de ”vet” ingenting. De är tränade på enorma textmängder där vissa ord och begrepp ofta förekommer tillsammans. Som James Wilkins påpekar: att frasen The Great Fire of London ofta följs av 1666 handlar inte om kunskap – utan om sannolikhet.
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


