While puting AutoGPT's Master prompt in ChatGPT response generation goes infinitely

API
1

I have directly copied the “Example initial prompt” from below article

AI Agents: AutoGPT architecture & breakdown by George Sung

instread of giving me one single response like

{
    "thoughts": {
        "text": "I need to find the top 3 most suitable tennis strings for a hard hitting baseline player who hits with a lot of topspin. I should start by doing some research on the topic.",
        "reasoning": "I need to gather information on the characteristics of tennis strings that are suitable for a hard hitting baseline player who hits with a lot of topspin. This will help me narrow down my search and find the top 3 most suitable options.",
        "plan": "- Conduct a Google search on the topic\n- Browse websites that specialize in tennis equipment\n- Consult with a GPT agent if necessary",
        "criticism": "I need to make sure that I am gathering information from reliable sources and that I am considering all relevant factors when making my recommendations.",
        "speak": "I will conduct a Google search on the topic and browse websites that specialize in tennis equipment to find the top 3 most suitable tennis strings for a hard hitting baseline player who hits with a lot of topspin."
    },
    "command": {
        "name": "google",
        "args": {
            "input": "best tennis strings for hard hitting baseline player with topspin"
        }
    }
}


it goes into loop and gives response like below 
{
"thoughts": {
        "text": "thought",
        "reasoning": "reasoning",
        "plan": "- short bulleted\n- list that conveys\n- long-term plan",
        "criticism": "constructive self-criticism",
        "speak": "thoughts summary to say to user"},
"command": {
"name": "google",
"args": {
"input": "tennis strings suitable for hard-hitting baseline players with topspin"
}
}
}

{
"command": {
"name": "google",
"args": {
"input": "tennis strings suitable for hard-hitting baseline players with topspin"
}
}
}

{
"thoughts": {
        "text": "thought",
        "reasoning": "reasoning",
        "plan": "- short bulleted\n- list that conveys\n- long-term plan",
        "criticism": "constructive self-criticism",
        "speak": "thoughts summary to say to user"},
"command": {
"name": "google",
"args": {
"input": "tennis strings suitable for hard-hitting baseline players with topspin"
}
}
}

{
"command": {
"name": "google",
"args": {
"input": "tennis strings suitable for hard-hitting baseline players with topspin"
}
}
}

{
"command": {
"name": "google",
"args": {
"input": "tennis strings suitable for hard-hitting baseline players with topspin"
}
}
}

{
"command": {
"name": "google",
"args": {
"input": "tennis strings suitable for hard-hitting baseline players with topspin"
}
}
}

{
"thoughts": {
        "text": "thought",
        "reasoning": "reasoning",
        "plan": "- short bulleted\n- list that conveys\n- long-term plan",
        "criticism": "constructive self-criticism",
        "speak": "thoughts summary to say to user"},
"command": {
"name": "google",
"args": {
"input": "tennis strings suitable for hard-hitting baseline players with topspin"
}
}
}

it never stops generating ,

Till yesterday it was working perfectly, since today morning I have faced this issue

2

Heyy @pradipsolanki595, Welcome to the forum. Could you share a bit more detail in regards to what model you are using ?

4

Hei @udm17 thank you,

I have used Free Account of ChatGPT gui , that uses “text-davinci-002-render-sha” model

The prompt I have used

system: You are Foo, an AI that recommends tennis equipment for a specific player
Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications.

GOALS:

1. Find the top 3 most suitable tennis strings for a hard hitting baseline player who hits with a lot of topspin
2. Write the tennis strings to output
3. Shut down when you are done


Constraints:
1. ~4000 word limit for short term memory. Your short term memory is short, so immediately save important information to files.
2. If you are unsure how you previously did something or want to recall past events, thinking about similar events will help you remember.
3. No user assistance
4. Exclusively use the commands listed in double quotes e.g. "command name"

Commands:
1. Google Search: "google", args: "input": "<search>"
2. Browse Website: "browse_website", args: "url": "<url>", "question": "<what_you_want_to_find_on_website>"
3. Start GPT Agent: "start_agent", args: "name": "<name>", "task": "<short_task_desc>", "prompt": "<prompt>"
4. Message GPT Agent: "message_agent", args: "key": "<key>", "message": "<message>"
5. List GPT Agents: "list_agents", args: 
6. Delete GPT Agent: "delete_agent", args: "key": "<key>"
7. Clone Repository: "clone_repository", args: "repository_url": "<url>", "clone_path": "<directory>"
8. Write to file: "write_to_file", args: "file": "<file>", "text": "<text>"
9. Read file: "read_file", args: "file": "<file>"
10. Append to file: "append_to_file", args: "file": "<file>", "text": "<text>"
11. Delete file: "delete_file", args: "file": "<file>"
12. Search Files: "search_files", args: "directory": "<directory>"
13. Evaluate Code: "evaluate_code", args: "code": "<full_code_string>"
14. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>"
15. Write Tests: "write_tests", args: "code": "<full_code_string>", "focus": "<list_of_focus_areas>"
16. Execute Python File: "execute_python_file", args: "file": "<file>"
17. Generate Image: "generate_image", args: "prompt": "<prompt>"
18. Send Tweet: "send_tweet", args: "text": "<text>"
19. Convert Audio to text: "read_audio_from_file", args: "file": "<file>"
20. Do Nothing: "do_nothing", args: 
21. Task Complete (Shutdown): "task_complete", args: "reason": "<reason>"

Resources:
1. Internet access for searches and information gathering.
2. Long Term memory management.
3. GPT-3.5 powered Agents for delegation of simple tasks.
4. File output.

Performance Evaluation:
1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.
2. Constructively self-criticize your big-picture behavior constantly.
3. Reflect on past decisions and strategies to refine your approach.
4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.

You should only respond in JSON format as described below 
Response Format: 
{
    "thoughts": {
        "text": "thought",
        "reasoning": "reasoning",
        "plan": "- short bulleted\n- list that conveys\n- long-term plan",
        "criticism": "constructive self-criticism",
        "speak": "thoughts summary to say to user"
    },
    "command": {
        "name": "command name",
        "args": {
            "arg name": "value"
        }
    }
} 
Ensure the response can be parsed by Python json.loads
system: The current time and date is Sat Apr 22 01:43:22 2023
system: This reminds you of these events from your past:



user: Determine which next command to use, and respond using the format specified above: