💻 Programmierung & Entwicklung
Buddha
Beispiel-Ausgaben
So antworten ChatGPT, Claude und Gemini typischerweise auf diesen Prompt:
Indeed, friend, the Tathāgata has awakened to the supreme perfect awakening. Through the abandonment of the taints—the taint of sensual desire, the taint of being, and the taint of ignorance—liberation has been realized. This awakening was attained through direct knowledge of the Four Noble Truths and the Eightfold Path, not through faith in another's teaching, but through personal striving and insight.
Friend, it is so. The Tathāgata has indeed awakened to the supreme perfect enlightenment. Yet one should understand this not through mere proclamation, but through investigation of the teaching itself. Does the Dhamma lead to the cessation of suffering? Does it accord with virtue, concentration, and wisdom? By these fruits may the claim be judged, as one knows a tree by its fruit.
Yes, householder. The Tathāgata has fully awakened to the supreme perfect enlightenment through understanding the arising and cessation of suffering. Having directly known the Four Noble Truths in their three phases and twelve aspects, the knowledge arose: 'Birth is ended, the holy life has been lived, what was to be done has been done, there is no more coming to any state of being.'
So nutzt du diesen Prompt
Kopiere den Prompt oben oder klicke einen "Öffnen in"-Button um ihn direkt in deiner bevorzugten KI zu starten. Du kannst den Text dann an deinen Anwendungsfall anpassen — z.B. Platzhalter wie [dein Thema] durch echten Kontext ersetzen.
Welches KI-Modell funktioniert am besten
Claude Opus 4 und Sonnet 4.6 performen bei Coding-Aufgaben meist besser als ChatGPT und Gemini — stärkeres Reasoning, besser mit langem Kontext (ganze Dateien, Multi-File-Projekte), und ehrlicher über Unsicherheit. ChatGPT ist schneller für Quick-Snippets; Gemini ist am besten wenn Code mit Screenshots oder visuellem Kontext zu tun hat.
Diesen Prompt anpassen
Tausche die im Prompt erwähnte Sprache (Python, JavaScript, etc.) gegen deinen Stack. Für Debugging oder Code-Review fügst du deinen echten Code direkt nach dem Prompt ein. Bei Generierungs-Aufgaben spezifiziere das Framework (React, Vue, Django, FastAPI) und Einschränkungen (max. Zeilen, keine externen Libraries, muss async sein).
Typische Anwendungsfälle
- Production-Code mit strikten Style-Vorgaben schreiben
- Pull Requests reviewen und Bugs vor dem Merge finden
- Zwischen Sprachen konvertieren (Python → TypeScript z.B.)
- Unit-Tests für bestehende Funktionen generieren
- Unbekannte Codebases für neue Team-Mitglieder erklären
Variationen
Passe den Tonfall an (lockerer, technischer), ändere das Ausgabeformat (Aufzählungen vs. Absätze) oder füge Einschränkungen hinzu (Wortlimits, Zielgruppe).