琐事生成器 - Anthropic

将此提示复制到我们的开发者控制台中，亲自尝试！

角色	内容
User	生成各种主题的琐事问题，并提供提示帮助用户得出正确答案。从多样化的类别中选择，创建测试用户知识或推理能力的问题。提供一系列越来越具体的提示，引导用户找到解决方案。确保问题具有挑战性，提示提供足够的信息来帮助用户，而不会过于轻易地泄露答案。

示例输出

类别：地理

问题：
世界上唯一一个同时与法国和西班牙接壤的国家是什么？

提示1：这个国家位于法国和西班牙之间的比利牛斯山脉中。
提示2：它以令人惊叹的山景、滑雪胜地和免税购物而闻名。
提示3：该国的首都名称中包含国家本身的名称。

答案：安道尔

类别：科学

问题：
植物通过什么过程将阳光、水和二氧化碳转化为能量和氧气？

提示1：这个过程对地球上的生命至关重要，因为它提供食物和氧气。
提示2：它主要发生在植物的叶子中。
提示3：该过程涉及叶绿素，一种吸收阳光的绿色色素。

答案：光合作用

类别：文学

问题：
谁写了1813年首次出版的经典小说《傲慢与偏见》？

提示1：这位作者是一位生活在1775年至1817年的英国女性。
提示2：她以机智、富有洞察力地描绘英国社会和礼仪而闻名。
提示3：她的其他著名作品包括《理智与情感》和《爱玛》。

答案：简·奥斯汀

类别：历史

问题：
分隔东西德的柏林墙在哪一年开始被拆除？

提示1：这一事件发生在20世纪晚期。
提示2：它标志着冷战结束的重要时刻。
提示3：这一年常与欧洲”共产主义倒台”这一短语联系在一起。

答案：1989年

API请求

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-4-20250514",
  max_tokens=2000,
  temperature=0.5,
  messages=[
    {
    "role": "user",
    "content": [
        {
          "type": "text",
          "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
        }
      ]
    }
  ]
)
print(message.content)

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-4-20250514",
  max_tokens=2000,
  temperature=0.5,
  messages=[
    {
    "role": "user",
    "content": [
        {
          "type": "text",
          "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
        }
      ]
    }
  ]
)
print(message.content)

import Anthropic from "@anthropic-ai/sdk";

const anthropic = new Anthropic({
  apiKey: "my_api_key", // defaults to process.env["ANTHROPIC_API_KEY"]
});

const msg = await anthropic.messages.create({
  model: "claude-opus-4-20250514",
  max_tokens: 2000,
  temperature: 0.5,
  messages: [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
        }
      ]
    }
  ]
});
console.log(msg);

from anthropic import AnthropicBedrock

# See https://docs.anthropic.com/claude/reference/claude-on-amazon-bedrock

# for authentication options

client = AnthropicBedrock()

message = client.messages.create(
model="anthropic.claude-opus-4-20250514-v1:0",
max_tokens=2000,
temperature=0.5,
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
}
]
}
]
)
print(message.content)

import AnthropicBedrock from "@anthropic-ai/bedrock-sdk";

// See https://docs.anthropic.com/claude/reference/claude-on-amazon-bedrock
// for authentication options
const client = new AnthropicBedrock();

const msg = await client.messages.create({
  model: "anthropic.claude-opus-4-20250514-v1:0",
  max_tokens: 2000,
  temperature: 0.5,
  messages: [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
        }
      ]
    }
  ]
});
console.log(msg);

from anthropic import AnthropicVertex

client = AnthropicVertex()

message = client.messages.create(
    model="claude-3-7-sonnet-v1@20250219",
    max_tokens=2000,
    temperature=0.5,
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
                }
            ]
        }
    ]
)
print(message.content)

import { AnthropicVertex } from '@anthropic-ai/vertex-sdk';

// Reads from the `CLOUD_ML_REGION` & `ANTHROPIC_VERTEX_PROJECT_ID` environment variables.
// Additionally goes through the standard `google-auth-library` flow.
const client = new AnthropicVertex();

const msg = await client.messages.create({
  model: "claude-3-7-sonnet-v1@20250219",
  max_tokens: 2000,
  temperature: 0.5,
  messages: [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
        }
      ]
    }
  ]
});
console.log(msg);

资源

​示例输出

​API请求

示例输出

API请求