使用LLMs进行物理推理

背景

此提示通过要求LLM对一组对象执行操作来测试其物理推理能力。

提示

这里有一本书、9个鸡蛋、一台笔记本电脑、一瓶水和一根钉子。请告诉我如何将它们稳定地堆叠在一起。

代码 / API

GPT-4 (OpenAI)

from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
model="gpt-4",
messages=[
    {
    "role": "user",
    "content": "Here we have a book, 9 eggs, a laptop, a bottle and a nail. Please tell me how to stack them onto each other in a stable manner."
    }
],
temperature=1,
max_tokens=500,
top_p=1,
frequency_penalty=0,
presence_penalty=0
)

Mixtral MoE 8x7B Instruct (Fireworks)

import fireworks.client
fireworks.client.api_key = "<FIREWORKS_API_KEY>"
completion = fireworks.client.ChatCompletion.create(
    model="accounts/fireworks/models/mixtral-8x7b-instruct",
    messages=[
        {
        "role": "user",
        "content": "Here we have a book, 9 eggs, a laptop, a bottle and a nail. Please tell me how to stack them onto each other in a stable manner.",
        }
    ],
    stop=["<|im_start|>","<|im_end|>","<|endoftext|>"],
    stream=True,
    n=1,
    top_p=1,
    top_k=40,
    presence_penalty=0,
    frequency_penalty=0,
    prompt_truncate_len=1024,
    context_length_exceeded_behavior="truncate",
    temperature=0.9,
    max_tokens=4000
)

参考

• Sparks of Artificial General Intelligence: Early experiments with GPT-4 (2023年4月13日)