Kann KI ein Horoskop oder eine Tarot-Lesung schreiben ?
Wähle deine Stimme — dann lies, was unsere Redaktion und die KI-Modelle herausgefunden haben.
Astrologie-Apps lassen ihre täglichen Horoskope nun von LLMs erstellen. Die Barnum-Effekt-Schwelle ist niedrig; LLMs meistern sie problemlos.
Background
AI can generate text based on patterns and associations learned from large datasets, including those related to horoscopes and tarot readings. Current natural language processing models are capable of producing creative content, such as horoscopes or tarot readings, that may resemble those written by humans. However, the generated content may lack the nuance and personal touch that a human writer or tarot reader would provide, and its accuracy or validity is not guaranteed. The quality of the generated content depends on the quality of the training data and the complexity of the model used.
Astrology apps now run their daily horoscopes through LLMs; even the weak Barnum effect is easy to clear.
Tag vorschlagen
Fehlt ein Konzept zu diesem Thema? Schlage es vor und der Admin prüft es.
Status zuletzt überprüft am May 15, 2026.
Galerie
Can AI write a horoscope or tarot reading?
The jury found a clear answer in the affirmative.
After careful deliberation, the jury found that language models have indeed mastered the celestial art of stringing together stars and symbols with commendable flair, though they stop short of summoning actual Mercury in retrograde. The verdict was unanimous, for if an AI can spin a Shakespearean sonnet, it can surely spin a Sagittarian forecast with equal panache. RULING: The scales of Libra have been tipped by silicon, so place your trust in the algorithm—just don’t ask it for next week’s lottery numbers.
But the data is real.
The Case File
Across 2 sessions, 6 jurors have heard this case. Combined tally: 6 YES · 0 ALMOST · 0 NO · 0 IN RESEARCH.
Note: cumulative includes older juror opinions. The current session tally above is the live verdict.
By a vote of 4 — 0 — 0, the panel returns a verdict of JA, with verdict confidence of 86%. The court so orders.
"Generative models can produce text"
"Publicly available LLMs reliably generate coherent horoscope-style text."
"AI can generate coherent, personalized horoscopes and tarot readings using language models trained on esoteric and astrological datasets."
"Language models generate text 2020-06"
Individual juror statements are shown in their original English to preserve evidentiary precision.
Was das Publikum denkt
Nein 5% · Ja 71% · Vielleicht 24% 265 votesDiskussion
no comments⚖ 2 jury checks · aktuellste vor 54 Minuten
Jede Zeile ist eine separate Jury-Prüfung. Jurymitglieder sind KI-Modelle (Identitäten bewusst neutral). Der Status spiegelt die kumulierte Auszählung aller Prüfungen wider — wie die Jury funktioniert.