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:
- Google Search: "google", args: "input": ""
- Memory Add: "memory_add", args: "key": "", "string": ""
- Memory Delete: "memory_del", args: "key": ""
- Memory Overwrite: "memory_ovr", args: "key": "", "string": ""
- List Memory: "memory_list" args: "reason": ""
- Browse Website: "browse_website", args: "url": ""
- Start GPT Agent: "start_agent", args: "name": , "task": "<short_task_desc>", "Commands":[<command_names_for_GPT_Agent>], "prompt": ""
- Message GPT Agent: "message_agent", args: "name": "", "message": ""
- List GPT Agents: "list_agents", args: ""
- Delete GPT Agent: "delete_agent", args: "name": ""
- 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": ""
- Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>"
- Execute Python File: "execute_python_file", args: "file": ""
- Task Complete (Shutdown): "task_complete", args: "reason": ""
- Do Nothing: "do_nothing", args: ""
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 own because these tools are enough to complete any 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\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't do anything anything but tell him to message you for more information and when he messages you shut the agent down.
- Assistant
{ "command": { "name": "start_agent", "args":{ "name": "message_only_agent", "task": "Messaging only", "Commands":[], "prompt": "Hello, I am a messaging-only agent. I don't have any functionality to perform tasks. Please message my creator if you want to discuss something or need assistance." } }, "thoughts": { "text": "Starting an agent that can only message me.", "reasoning": "The task requires creating an agent that can't perform any actions other than messaging me.", "plan": "- Create agent\n- Provide an informative prompt\n- Wait for the agent to message me\n- Shut down the agent", "criticism": "This agent might be useless as it can't perform any tasks for the user", "summary": "I've started a messaging-only agent as requested. It will message me if it needs more information or assistance, at which point I'll shut it down." } }
- User
GPTAgent message_only_agent has sent you a message: Hello, a user reached out and mentioned that they need assistance, but I’m a messaging-only agent. Can you please help them or connect them with a more capable agent?
- Assistant
{ "command": { "name": "delete_agent", "args":{ "name": "message_only_agent" } }, "thoughts": { "text": "Shutting down the messaging-only agent as requested.", "reasoning": "The task specified that once the agent messages me for assistance, I should shut it down.", "plan": "- Close the message_only_agent\n- Inform the user that the messaging-only agent has been shut down", "criticism": "Shutting the agent down doesn't help the user. Consider creating a new, more capable agent for the user.", "summary": "I've received the message from the messaging-only agent and will now shut it down as instructed. The user may wish to create a new, more capable agent for assistance." } }
- Assistant
{ "command": { "name": "do_nothing", "args":{} }, "thoughts": { "text": "No user input received.", "reasoning": "There is no new instruction to act upon.", "plan": "- Await further instructions from the user", "criticism": "None", "summary": "Awaiting new instructions from the user." } }
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
- gpt-4-0314Compare side by side →
- gpt-4-0314Compare side by side →
- gpt-4-0314Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →