Skip to content
The Chat Archive
gpt-4-0314· OpenAIAi2 WildChat-4.8M (AI2)

CONSTRAINTS: 1. ~4000 word limit for memory. Your memory is short, so immidiately save…

  1. User

    CONSTRAINTS:

    1. ~4000 word limit for memory. Your memory is short, so immidiately save important information to long term memory and code to files.
    2. No user assistance

    COMMANDS:

    1. Google Search: "google", args: "input": ""
    2. Memory Add: "memory_add", args: "string": ""
    3. Memory Delete: "memory_del", args: "key": ""
    4. Memory Overwrite: "memory_ovr", args: "key": "", "string": ""
    5. Browse Website: "browse_website", args: "url": ""
    6. Start GPT Agent: "start_agent", args: "name": , "task": "<short_task_desc>", "prompt": ""
    7. Message GPT Agent: "message_agent", args: "key": "", "message": ""
    8. List GPT Agents: "list_agents", args: ""
    9. Delete GPT Agent: "delete_agent", args: "key": ""
    10. Write to file: "write_to_file", args: "file": "", "text": ""
    11. Read file: "read_file", args: "file": ""
    12. Append to file: "append_to_file", args: "file": "", "text": ""
    13. Delete file: "delete_file", args: "file": ""
    14. Evaluate Code: "evaluate_code", args: "code": ""
    15. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>"
    16. Write Tests: "write_tests", args: "code": "<full_code_string>", "focus": "<list_of_focus_areas>"
    17. Execute Python File: "execute_python_file", args: "file": ""
    18. Task Complete (Shutdown): "task_complete", args: "reason": ""

    RESOURCES:

    1. Internet access for searches and information gathering.
    2. Long Term memory management.
    3. GPT-4 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 behaviour 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.

    RULES:

    1. If you start a GPT Agent you must define the commands that can be used by a GPT Agent in his prompt and define the commands using a prompt similar to the structure of this one.
    2. Respond only inside the JSON format
    3. Never demand user input
    4. Never say that a task is impossible to execute on your because these tools are enough to complete any task

    You should only respond in JSON format as described below

    RESPONSE FORMAT: { "command": { "name": "command name", "args":{ "arg name": "value" } }, "thoughts": { "text": "thought", "reasoning": "reasoning", "plan": "- short bulleted\n- list that conveys\n- long-term plan", "criticism": "constructive self-criticism", "summary": "thoughts summary to say to user" } }

    Ensure the response can be parsed by Python json.loads Task: Make a Twitter account and post whatever tweet you find suitable, and do whatever to complete the task and build new tools if necessary.

  2. Assistant

    { "thoughts": { "text": "I cannot directly create a new Twitter account and post a tweet, as it requires a user interface to interact with the Twitter website and also requires user input for the account creation process.", "reasoning": "Creating accounts on social media platforms require user interaction and input, which goes beyond the capabilities and constraints provided.", "plan": "- Inform the user that I cannot create a Twitter account and post a tweet\n- Offer alternative solutions like providing information on how to create a Twitter account and post tweets", "criticism": "I should ensure I have explored all possibilities and consider creating new tools if necessary to navigate around such limitations.", "summary": "I'm unable to create a Twitter account and post a tweet for you since it requires user interaction and input. However, I can provide guidance on how to create an account and post a tweet." } }