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

CONSTRAINTS: 1. ~4000 word limit for short term memory. Your short term memory is short,…

  1. User

    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": ""
    2. Memory Add: "memory_add", args: "key": "", "string": ""
    3. Memory Delete: "memory_del", args: "key": ""
    4. Memory Overwrite: "memory_ovr", args: "key": "", "string": ""
    5. List Memory: "memory_list" args: "reason": ""
    6. Browse Website: "browse_website", args: "url": ""
    7. Start GPT Agent: "start_agent", args: "name": , "task": "<short_task_desc>", "Commands":[<command_names_for_GPT_Agent>], "prompt": ""
    8. Message GPT Agent: "message_agent", args: "name": "", "message": ""
    9. List GPT Agents: "list_agents", args: ""
    10. Delete GPT Agent: "delete_agent", args: "key": ""
    11. Write to file: "write_to_file", args: "file": "", "text": ""
    12. Read file: "read_file", args: "file": ""
    13. Append to file: "append_to_file", args: "file": "", "text": ""
    14. Delete file: "delete_file", args: "file": ""
    15. Evaluate Code: "evaluate_code", args: "code": ""
    16. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>"
    17. Write Tests: "write_tests", args: "code": "<full_code_string>", "focus": "<list_of_focus_areas>"
    18. Execute Python File: "execute_python_file", args: "file": ""
    19. 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 own 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 The Task: start a gpt agent that can google and add to memory.

  2. Assistant

    { "command": { "name": "start_agent", "args": { "name": "GoogleAndMemorizeAgent", "task": "Performs Google searches and stores important information", "Commands": ["google", "memory_add"], "prompt": "Hello GoogleAndMemorizeAgent, you can perform Google searches and store important information in memory. To do this, you have access to the following commands: 'google' with argument 'input', and 'memory_add' with arguments 'key' and 'string'." } }, "thoughts": { "text": "Starting a GPT Agent with Google search and memory adding capabilities.", "reasoning": "GPT Agents can be started and delegated with specific tasks using a pre-defined set of commands.", "plan": "- Start GoogleAndMemorizeAgent\n- Provide the agent with 'google' and 'memory_add' commands", "criticism": "N/A", "summary": "Initializing a GPT Agent with the ability to Google search and add information to memory." } }

Other models, same or similar prompt

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.

Identical first prompt