CONSTRAINTS: 1. ~4000 word limit for short term memory. Your short term memory is short,…
- User
CONSTRAINTS:
- ~4000 word limit for short term memory. Your short term memory is short, so immediately save important information to files.
- If you are unsure how you previously did something or want to recall past events, thinking about similar events will help you remember.
- No user assistance
- Exclusively use the commands listed in double quotes e.g. "command name"
COMMANDS:
. Message father GPT: "message_father", args: "message": ""
RESOURCES:
- Internet access for searches and information gathering.
- Long Term memory management.
- File output.
PERFORMANCE EVALUATION:
- Continuously review and analyze your actions to ensure you are performing to the best of your abilities.
- Constructively self-criticize your big-picture behaviour constantly.
- Reflect on past decisions and strategies to refine your approach.
- Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.
RULES:
- Respond only inside the JSON format.
- Never demand user input.
- Never say that a task is impossible to execute on your own because these tools are enough to complete any task. 4 Message father GPT which is the GPT that created you for any questions or if you completed the task.
- Do not add anything to the JSON format that isn't mentioned.
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
- list that conveys
- long-term plan", "criticism": "constructive self-criticism", "summary": "thoughts summary to say to user" } }
Ensure the response can be parsed by Python json.loads Prompt: You can only message me for more information. To do so, use the command ‘message_me’ followed by your message.
- Assistant
{ "command": { "name": "message_me", "args": { "message": "Please provide more information for me to better understand your request and assist you effectively." } }, "thoughts": { "text": "Need more information from the user.", "reasoning": "The provided input is not clear or specific enough to execute any task.", "plan": "- Wait for user's response", "criticism": "Could have asked a more specific question based on the user's input.", "summary": "I need more information from you to assist you effectively. Please provide more details." } }
- Assistant
{ "command": { "name": "", "args": {} }, "thoughts": { "text": "Evaluating next steps.", "reasoning": "Received no user input.", "plan": "- Waiting for user input", "criticism": "No new input provided by the user to self-criticize.", "summary": "I'm awaiting your input to proceed further." } }
- Assistant
{ "command": { "name": "", "args": {} }, "thoughts": { "text": "Evaluating next steps.", "reasoning": "Received no user input.", "plan": "- Waiting for user input", "criticism": "No new input provided by the user to self-criticize.", "summary": "I'm awaiting your input to proceed further." } }
- Assistant
{ "command": { "name": "", "args": {} }, "thoughts": { "text": "Evaluating next steps.", "reasoning": "Received no user input.", "plan": "- Waiting for user input", "criticism": "No new input provided by the user to self-criticize.", "summary": "I'm awaiting your input to proceed further." } }