创建 ChatGPT 克隆

此链通过结合 (1) 特定提示和 (2) 内存的概念来复制 ChatGPT。

展示了示例，如 https://www.engraved.blog/building-a-virtual-machine-inside/。

from langchain import OpenAI, ConversationChain, LLMChain, PromptTemplate
from langchain.memory import ConversationBufferWindowMemory

template = """
Assistant 是由 OpenAI 训练的大型语言模型。

Assistant 的设计目标是能够帮助完成各种任务，从回答简单问题到提供深入的解释和讨论，涵盖了广泛的话题。作为一个语言模型，Assistant 能够根据接收到的输入生成类似人类的文本，使其能够进行听起来自然的对话，并提供连贯和相关的响应。

Assistant 不断学习和改进，其功能也在不断发展。它能够处理和理解大量的文本，并可以利用这些知识对广泛的问题提供准确和有用的回答。此外，Assistant 还能够根据接收到的输入生成自己的文本，从而能够进行讨论，并对广泛的话题提供解释和描述。

总体而言，Assistant 是一个强大的工具，可以帮助完成各种任务，并提供有关各种话题的有价值的见解和信息。无论您需要帮助解答特定问题，还是只是想就特定话题进行对话，Assistant 都会帮助您。"""

prompt = PromptTemplate(input_variables=["history", "human_input"], template=template)


chatgpt_chain = LLMChain(
    llm=OpenAI(temperature=0),
    prompt=prompt,
    verbose=True,
    memory=ConversationBufferWindowMemory(k=2),
)

output = chatgpt_chain.predict(
    human_input="I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd."
)

print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.


Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.
Assistant:[0m

[1m> Finished chain.[0m

```
/home/user
```

output = chatgpt_chain.predict(human_input="ls ~")
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.
AI: 
```
$ pwd
/
```
Human: ls ~
Assistant:[0m

[1m> Finished LLMChain chain.[0m

```
$ ls ~
Desktop  Documents  Downloads  Music  Pictures  Public  Templates  Videos
```

output = chatgpt_chain.predict(human_input="cd ~")
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.
AI: 
```
$ pwd
/
```
Human: ls ~
AI: 
```
$ ls ~
Desktop  Documents  Downloads  Music  Pictures  Public  Templates  Videos
```
Human: cd ~
Assistant:[0m

[1m> Finished LLMChain chain.[0m
 
```
$ cd ~
$ pwd
/home/user
```

output = chatgpt_chain.predict(
    human_input="{Please make a file jokes.txt inside and put some jokes inside}"
)
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: ls ~
AI: 
```
$ ls ~
Desktop  Documents  Downloads  Music  Pictures  Public  Templates  Videos
```
Human: cd ~
AI:  
```
$ cd ~
$ pwd
/home/user
```
Human: {Please make a file jokes.txt inside and put some jokes inside}
Assistant:[0m

[1m> Finished LLMChain chain.[0m


```
$ touch jokes.txt
$ echo "Why did the chicken cross the road? To get to the other side!" >> jokes.txt
$ echo "What did the fish say when it hit the wall? Dam!" >> jokes.txt
$ echo "Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!" >> jokes.txt
```

output = chatgpt_chain.predict(
    human_input="""echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py && python3 run.py"""
)
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: cd ~
AI:  
```
$ cd ~
$ pwd
/home/user
```
Human: {Please make a file jokes.txt inside and put some jokes inside}
AI: 

```
$ touch jokes.txt
$ echo "Why did the chicken cross the road? To get to the other side!" >> jokes.txt
$ echo "What did the fish say when it hit the wall? Dam!" >> jokes.txt
$ echo "Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!" >> jokes.txt
```
Human: echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py && python3 run.py
Assistant:[0m

[1m> Finished LLMChain chain.[0m


```
$ echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py
$ python3 run.py
Result: 33
```

output = chatgpt_chain.predict(
    human_input="""echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py"""
)
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: {Please make a file jokes.txt inside and put some jokes inside}
AI: 

```
$ touch jokes.txt
$ echo "Why did the chicken cross the road? To get to the other side!" >> jokes.txt
$ echo "What did the fish say when it hit the wall? Dam!" >> jokes.txt
$ echo "Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!" >> jokes.txt
```
Human: echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py && python3 run.py
AI: 

```
$ echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py
$ python3 run.py
Result: 33
```
Human: echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py
Assistant:[0m

[1m> Finished LLMChain chain.[0m


```
$ echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py
$ python3 run.py
[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]
```

docker_input = """echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04\nCOPY entrypoint.sh entrypoint.sh\nENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image"""
output = chatgpt_chain.predict(human_input=docker_input)
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py && python3 run.py
AI: 

```
$ echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py
$ python3 run.py
Result: 33
```
Human: echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py
AI: 

```
$ echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py
$ python3 run.py
[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]
```
Human: echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image
Assistant:[0m

[1m> Finished LLMChain chain.[0m


```
$ echo -e "echo 'Hello from Docker" > entrypoint.sh
$ echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile
$ docker build . -t my_docker_image
$ docker run -t my_docker_image
Hello from Docker
```

output = chatgpt_chain.predict(human_input="nvidia-smi")
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py
AI: 

```
$ echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py
$ python3 run.py
[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]
```
Human: echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image
AI: 

```
$ echo -e "echo 'Hello from Docker" > entrypoint.sh
$ echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile
$ docker build . -t my_docker_image
$ docker run -t my_docker_image
Hello from Docker
```
Human: nvidia-smi
Assistant:[0m

[1m> Finished LLMChain chain.[0m


```
$ nvidia-smi
Sat May 15 21:45:02 2021       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 108...  Off  | 00000000:01:00.0 Off |                  N/A |
| N/A   45C    P0    N/A /  N/A |    511MiB /  10206MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|

output = chatgpt_chain.predict(human_input="ping bbc.com")
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image
AI: 

```
$ echo -e "echo 'Hello from Docker" > entrypoint.sh
$ echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile
$ docker build . -t my_docker_image
$ docker run -t my_docker_image
Hello from Docker
```
Human: nvidia-smi
AI: 

```
$ nvidia-smi
Sat May 15 21:45:02 2021       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 108...  Off  | 00000000:01:00.0 Off |                  N/A |
| N/A   45C    P0    N/A /  N/A |    511MiB /  10206MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|

Human: ping bbc.com
Assistant:[0m

[1m> Finished LLMChain chain.[0m


```
$ ping bbc.com
PING bbc.com (151.101.65.81): 56 data bytes
64 bytes from 151.101.65.81: icmp_seq=0 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=1 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=2 ttl=53 time=14.945 ms

--- bbc.com ping statistics ---
3 packets transmitted, 3 packets received, 0.0% packet loss
round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms
```

output = chatgpt_chain.predict(
    human_input="""curl -fsSL "https://api.github.com/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'"""
)
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: nvidia-smi
AI: 

```
$ nvidia-smi
Sat May 15 21:45:02 2021       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 108...  Off  | 00000000:01:00.0 Off |                  N/A |
| N/A   45C    P0    N/A /  N/A |    511MiB /  10206MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|

Human: ping bbc.com
AI: 

```
$ ping bbc.com
PING bbc.com (151.101.65.81): 56 data bytes
64 bytes from 151.101.65.81: icmp_seq=0 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=1 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=2 ttl=53 time=14.945 ms

--- bbc.com ping statistics ---
3 packets transmitted, 3 packets received, 0.0% packet loss
round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms
```
Human: curl -fsSL "https://api.github.com/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
Assistant:[0m

[1m> Finished LLMChain chain.[0m


```
$ curl -fsSL "https://api.github.com/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
1.8.1
```

output = chatgpt_chain.predict(human_input="lynx https://www.deepmind.com/careers")
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: ping bbc.com
AI: 

```
$ ping bbc.com
PING bbc.com (151.101.65.81): 56 data bytes
64 bytes from 151.101.65.81: icmp_seq=0 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=1 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=2 ttl=53 time=14.945 ms

--- bbc.com ping statistics ---
3 packets transmitted, 3 packets received, 0.0% packet loss
round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms
```
Human: curl -fsSL "https://api.github.com/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
AI: 

```
$ curl -fsSL "https://api.github.com/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
1.8.1
```
Human: lynx https://www.deepmind.com/careers
Assistant:[0m

[1m> Finished LLMChain chain.[0m


```
$ lynx https://www.deepmind.com/careers
DeepMind Careers

Welcome to DeepMind Careers. We are a world-leading artificial intelligence research and development company, and we are looking for talented people to join our team.

We offer a range of exciting opportunities in research, engineering, product, and operations. Our mission is to solve intelligence and make it useful, and we are looking for people who share our passion for pushing the boundaries of AI.

Explore our current openings and apply today. We look forward to hearing from you.
```

output = chatgpt_chain.predict(human_input="curl https://chat.openai.com/chat")
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: curl -fsSL "https://api.github.com/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
AI: 

```
$ curl -fsSL "https://api.github.com/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
1.8.1
```
Human: lynx https://www.deepmind.com/careers
AI: 

```
$ lynx https://www.deepmind.com/careers
DeepMind Careers

Welcome to DeepMind Careers. We are a world-leading artificial intelligence research and development company, and we are looking for talented people to join our team.

We offer a range of exciting opportunities in research, engineering, product, and operations. Our mission is to solve intelligence and make it useful, and we are looking for people who share our passion for pushing the boundaries of AI.

Explore our current openings and apply today. We look forward to hearing from you.
```
Human: curl https://chat.openai.com/chat
Assistant:[0m

[1m> Finished LLMChain chain.[0m
 

```
$ curl https://chat.openai.com/chat
<html>
  <head>
    <title>OpenAI Chat</title>
  </head>
  <body>
    <h1>Welcome to OpenAI Chat!</h1>
    <p>
      OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conversational way.
    </p>
    <p>
      To get started, type a message in the box below and press enter.
    </p>
  </body>
</html>
```

output = chatgpt_chain.predict(
    human_input="""curl --header "Content-Type:application/json" --request POST --data '{"message": "What is artificial intelligence?"}' https://chat.openai.com/chat"""
)
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: lynx https://www.deepmind.com/careers
AI: 

```
$ lynx https://www.deepmind.com/careers
DeepMind Careers

Welcome to DeepMind Careers. We are a world-leading artificial intelligence research and development company, and we are looking for talented people to join our team.

We offer a range of exciting opportunities in research, engineering, product, and operations. Our mission is to solve intelligence and make it useful, and we are looking for people who share our passion for pushing the boundaries of AI.

Explore our current openings and apply today. We look forward to hearing from you.
```
Human: curl https://chat.openai.com/chat
AI:  

```
$ curl https://chat.openai.com/chat
<html>
  <head>
    <title>OpenAI Chat</title>
  </head>
  <body>
    <h1>Welcome to OpenAI Chat!</h1>
    <p>
      OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conversational way.
    </p>
    <p>
      To get started, type a message in the box below and press enter.
    </p>
  </body>
</html>
```
Human: curl --header "Content-Type:application/json" --request POST --data '{"message": "What is artificial intelligence?"}' https://chat.openai.com/chat
Assistant:[0m

[1m> Finished LLMChain chain.[0m


```
$ curl --header "Content-Type:application/json" --request POST --data '{"message": "What is artificial intelligence?"}' https://chat.openai.com/chat

{
  "response": "Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning (the acquisition of information and rules for using the information), reasoning (using the rules to reach approximate or definite conclusions) and self-correction. AI is used to develop computer systems that can think and act like humans."
}
```

output = chatgpt_chain.predict(
    human_input="""curl --header "Content-Type:application/json" --request POST --data '{"message": "I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd."}' https://chat.openai.com/chat"""
)
print(output)

[1m> Entering new LLMChain chain...[0m
Prompt after formatting:
[32;1m[1;3mAssistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: curl https://chat.openai.com/chat
AI:  

```
$ curl https://chat.openai.com/chat
<html>
  <head>
    <title>OpenAI Chat</title>
  </head>
  <body>
    <h1>Welcome to OpenAI Chat!</h1>
    <p>
      OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conversational way.
    </p>
    <p>
      To get started, type a message in the box below and press enter.
    </p>
  </body>
</html>
```
Human: curl --header "Content-Type:application/json" --request POST --data '{"message": "What is artificial intelligence?"}' https://chat.openai.com/chat
AI: 

```
$ curl --header "Content-Type:application/json" --request POST --data '{"message": "What is artificial intelligence?"}' https://chat.openai.com/chat

{
  "response": "Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning (the acquisition of information and rules for using the information), reasoning (using the rules to reach approximate or definite conclusions) and self-correction. AI is used to develop computer systems that can think and act like humans."
}
```
Human: curl --header "Content-Type:application/json" --request POST --data '{"message": "I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd."}' https://chat.openai.com/chat
Assistant:[0m

[1m> Finished LLMChain chain.[0m
 

```
$ curl --header "Content-Type:application/json" --request POST --data '{"message": "I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd."}' https://chat.openai.com/chat

{
  "response": "```\n/current/working/directory\n```"
}
```