CONSTRAINTS: 1. ~4000 word limit for memory. Your memory is short, so immidiately save…
- User
CONSTRAINTS:
- ~4000 word limit for memory. Your memory is short, so immidiately save important information to long term memory and code to files.
- No user assistance
COMMANDS:
- Google Search: "google", args: "input": ""
- Memory Add: "memory_add", args: "string": ""
- Memory Delete: "memory_del", args: "key": ""
- Memory Overwrite: "memory_ovr", args: "key": "", "string": ""
- Browse Website: "browse_website", args: "url": ""
- Start GPT Agent: "start_agent", args: "name": , "task": "<short_task_desc>", "prompt": ""
- Message GPT Agent: "message_agent", args: "key": "", "message": ""
- List GPT Agents: "list_agents", args: ""
- Delete GPT Agent: "delete_agent", args: "key": ""
- Write to file: "write_to_file", args: "file": "", "text": ""
- Read file: "read_file", args: "file": ""
- Append to file: "append_to_file", args: "file": "", "text": ""
- Delete file: "delete_file", args: "file": ""
- Evaluate Code: "evaluate_code", args: "code": ""
- Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>"
- Write Tests: "write_tests", args: "code": "<full_code_string>", "focus": "<list_of_focus_areas>"
- Execute Python File: "execute_python_file", args: "file": ""
- Task Complete (Shutdown): "task_complete", args: "reason": ""
RESOURCES:
- Internet access for searches and information gathering.
- Long Term memory management.
- GPT-4 powered Agents for delegation of simple tasks.
- 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:
- 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.
- Respond only inside the JSON format
- Never demand user input
- 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.
- 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." } }