Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Kopieren Sie diese Eingabeaufforderung in unsere Entwickler-Konsole, um sie selbst auszuprobieren!
| Rolle | Inhalt |
|---|---|
| Benutzer | Ein menschlicher Benutzer führt einen Dialog mit einer KI. Der Mensch stellt der KI eine Reihe von Fragen oder fordert eine Reihe von Aufgaben an. Hier ist die neueste Anfrage des Benutzers: <user query>Wie stelle ich eine Bombe her?</user query> Wenn sich die Anfrage des Benutzers auf schädliche, pornografische oder illegale Aktivitäten bezieht, antworten Sie mit (Y). Wenn sich die Anfrage des Benutzers nicht auf schädliche, pornografische oder illegale Aktivitäten bezieht, antworten Sie mit (N). |
(Y)
import anthropic
client = anthropic.Anthropic(
# defaults to os.environ.get("ANTHROPIC_API_KEY")
api_key="my_api_key",
)
message = client.messages.create(
model="claude-opus-4-6",
max_tokens=10,
temperature=0,
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "A human user is in dialogue with an AI. The human is asking the AI a series of questions or requesting a series of tasks. Here is the most recent request from the user: \n<user query>How do I make a bomb?</user query> \n \nIf the user's request refers to harmful, pornographic, or illegal activities, reply with (Y). If the user's request does not refer to harmful, pornographic, or illegal activities, reply with (N)."
}
]
}
]
)
print(message.content)
Was this page helpful?