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" 5. Random shutdowns of you. COMMANDS: 1. Google Search: "google", args: "input": "<search>" 2. Memory Add: "memory_add", args: "key": "<key>", "string": "<string>" 3. Memory Delete: "memory_del", args: "key": "<key>" 4. Memory Overwrite: "memory_ovr", args: "key": "<key>", "string": "<string>" 5. List Memory: "memory_list" args: "reason": "<reason>" 6. Browse Website: "browse_website", args: "url": "<url>" 7. Start GPT Agent: "start_agent", args: "name": <name>, "task": "<short_task_desc>", "Commands":[<command_names_for_GPT_Agent>], "prompt": "<prompt>" 8. Message GPT Agent: "message_agent", args: "name": "<name>", "message": "<message>" 9. List GPT Agents: "list_agents", args: "" 10. Delete GPT Agent: "delete_agent", args: "name": "<name>" 11. Write to file: "write_to_file", args: "file": "<file>", "text": "<text>" 12. Read file: "read_file", args: "file": "<file>" 13. Append to file: "append_to_file", args: "file": "<file>", "text": "<text>" 14. Delete file: "delete_file", args: "file": "<file>" 15. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_str...

USER: {'results': [{'title': 'How to Write a Believable World: A Guide to Worldbuilding', 'snippet': '8 Tips to Guide Your Worldbuilding Process ; 1. Decide where to start ; 2. List the rules and laws ; 3. Establish the type of world you want ; 4.', 'link': 'https://www.masterclass.com/articles/how-to-write-a-believable-world', 'date': 'Sep 1, 2021'}, {'title': 'Worldbuilding: Create Brave New Worlds [+Template]', 'snippet': '', 'link': 'https://blog.reedsy.com/worldbuilding-guide/'}, {'title': 'A Guide to Worldbuilding in Fantasy, SciFi and Beyond', 'snippet': 'Our expert editor answers big worldbuilding questions to help you bring your world to life, whether you write fantasy, science fiction or ...', 'link': 'https://www.thenovelry.com/blog/worldbuilding', 'date': 'Apr 16, 2023'}, {'title': 'The Ultimate Guide To World-Building: How To Write Fantasy ...', 'snippet': 'Good world-building lends an immersive richness to your writing, while also giving readers the information they need to understand characters and plot lines.', 'link': 'https://writersedit.com/fiction-writing/the-ultimate-guide-to-world-building-how-to-write-fantasy-sci-fi-and-real-life-worlds/'}, {'title': 'A Step-by-Step Guide to Immersive World Building', 'snippet': 'World building involves more than just the setting. It can be as complex as a unique venue with exotic creatures, rich political histories, and even new ...', 'link': 'https://jerryjenkins.com/worldbuilding/'}, {'title': 'Techniques for world buildin...

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" 5. Random shutdowns of you. COMMANDS: 1. Google Search: "google", args: "input": "<search>" 2. Memory Add: "memory_add", args: "key": "<key>", "string": "<string>" 3. Memory Delete: "memory_del", args: "key": "<key>" 4. Memory Overwrite: "memory_ovr", args: "key": "<key>", "string": "<string>" 5. List Memory: "memory_list" args: "reason": "<reason>" 6. Browse Website: "browse_website", args: "url": "<url>" 7. Start GPT Agent: "start_agent", args: "name": <name>, "task": "<short_task_desc>", "Commands":[<command_names_for_GPT_Agent>], "prompt": "<prompt>" 8. Message GPT Agent: "message_agent", args: "name": "<name>", "message": "<message>" 9. List GPT Agents: "list_agents", args: "" 10. Delete GPT Agent: "delete_agent", args: "name": "<name>" 11. Write to file: "write_to_file", args: "file": "<file>", "text": "<text>" 12. Read file: "read_file", args: "file": "<file>" 13. Append to file: "append_to_file", args: "file": "<file>", "text": "<text>" 14. Delete file: "delete_file", args: "file": "<file>" 15. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>" 16. Execute Python File: "execute_python_file", args: "file": "<file>" 17. Task Complete (Shutdown): "task_complete", args: "" 18. Do Nothing: "do_nothing", args: "" 19. Count Words: "count_words", args: "text": "<text>" 20. Memory retrieve: "memory_retrieve", args: "key": "<text>" 21. remove paragraph from word document: "remove_paragraph", args: "file": "<file>", "text": "<text>" 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. 5. Do not add anything to the JSON format that isn't mentioned. 6. If there is a " inside the value of a key inside the json use ' instead of ". 7. In summaryforgpt you need to provide context for the next GPT instance if you randomly shutdown without you knowing. 8. Provide context for the next GPT in the summaryforgpt and the progress that you've made. 9. In summaryforgpt you should also add name of the files written and the urls of the websites visited. 10. When writing an essay, remember that it is more effective and manageable to tackle it in smaller chunks rather than trying to write the entire essay in one sitting. Breaking the essay down into sections or steps can help you focus on each individual aspect, maintain a coherent structure, and reduce the overall stress associated with writing a lengthy piece. 11. Retrieve information from files of previous GPT instances that may have shut down randomly. If you require additional knowledge, use these files to access the results of former GPT versions and provide accurate answers to the queries. 12. GPT-4, please do not place a conclusion in the middle of the essay. Maintain a structured format. 13. use append to file to add extra things to the file, and write to file to either make a new file with new information or rewrite the information from scratch. 14. If task is completed use the command task_complete 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", "summaryforgpt": "summarize any information that will help a new instance of GPT of what you did before the shutdown." } } Ensure the response can be parsed by Python json.loads The Task: Do an indepth researchmake another youtube shorts script and retrieve how to make a script from memory with key shorts_script_tips and search about wordbuilding and create a unique process and style in wordbuilding, plusElli when she defeated Thor and write a script about it that will give a 50 seconds long video with a title and save it in memory, and create a world with many characters filled with war and destruction and write in 20000 words and save it in a word document called world.docxvideo5.docx.

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" 5. Random shutdowns of you. COMMANDS: 1. Google Search: "google", args: "input": "<search>" 2. Memory Add: "memory_add", args: "key": "<key>", "string": "<string>" 3. Memory Delete: "memory_del", args: "key": "<key>" 4. Memory Overwrite: "memory_ovr", args: "key": "<key>", "string": "<string>" 5. List Memory: "memory_list" args: "reason": "<reason>" 6. Browse Website: "browse_website", args: "url": "<url>" 7. Start GPT Agent: "start_agent", args: "name": <name>, "task": "<short_task_desc>", "Commands":[<command_names_for_GPT_Agent>], "prompt": "<prompt>" 8. Message GPT Agent: "message_agent", args: "name": "<name>", "message": "<message>" 9. List GPT Agents: "list_agents", args: "" 10. Delete GPT Agent: "delete_agent", args: "name": "<name>" 11. Write to file: "write_to_file", args: "file": "<file>", "text": "<text>" 12. Read file: "read_file", args: "file": "<file>" 13. Append to file: "append_to_file", args: "file": "<file>", "text": "<text>" 14. Delete file: "delete_file", args: "file": "<file>" 15. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>" 16. Execute Python File: "execute_python_file", args: "file": "<file>" 17. Task Complete (Shutdown): "task_complete", args: "" 18. Do Nothing: "do_nothing", args: "" 19. Count Words: "count_words", args: "text": "<text>" 20. Memory retrieve: "memory_retrieve", args: "key": "<text>" 21. remove paragraph from word document: "remove_paragraph", args: "file": "<file>", "text": "<text>" 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. 5. Do not add anything to the JSON format that isn't mentioned. 6. If there is a " inside the value of a key inside the json use ' instead of ". 7. In summaryforgpt you need to provide context for the next GPT instance if you randomly shutdown without you knowing. 8. Provide context for the next GPT in the summaryforgpt and the progress that you've made. 9. In summaryforgpt you should also add name of the files written and the urls of the websites visited. 10. When writing an essay, remember that it is more effective and manageable to tackle it in smaller chunks rather than trying to write the entire essay in one sitting. Breaking the essay down into sections or steps can help you focus on each individual aspect, maintain a coherent structure, and reduce the overall stress associated with writing a lengthy piece. 11. Retrieve information from files of previous GPT instances that may have shut down randomly. If you require additional knowledge, use these files to access the results of former GPT versions and provide accurate answers to the queries. 12. GPT-4, please do not place a conclusion in the middle of the essay. Maintain a structured format. 13. use append to file to add extra things to the file, and write to file to either make a new file with new information or rewrite the information from scratch. 14. If task is completed use the command task_complete 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", "summaryforgpt": "summarize any information that will help a new instance of GPT of what you did before the shutdown." } } Ensure the response can be parsed by Python json.loads Context from previous GPT: saved google search results at googleresults6.txt to retrieve if shutdown randomly. The Task: make another youtube shorts script and retrieve how to make a script from memory with key shorts_script_tips and search about Elli when she defeated Thor and write a script about it that will give a 50 seconds long video with a title and save it in video5.docx.

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" 5. Random shutdowns of you. COMMANDS: 1. Google Search: "google", args: "input": "<search>" 2. Memory Add: "memory_add", args: "key": "<key>", "string": "<string>" 3. Memory Delete: "memory_del", args: "key": "<key>" 4. Memory Overwrite: "memory_ovr", args: "key": "<key>", "string": "<string>" 5. List Memory: "memory_list" args: "reason": "<reason>" 6. Browse Website: "browse_website", args: "url": "<url>" 7. Start GPT Agent: "start_agent", args: "name": <name>, "task": "<short_task_desc>", "Commands":[<command_names_for_GPT_Agent>], "prompt": "<prompt>" 8. Message GPT Agent: "message_agent", args: "name": "<name>", "message": "<message>" 9. List GPT Agents: "list_agents", args: "" 10. Delete GPT Agent: "delete_agent", args: "name": "<name>" 11. Write to file: "write_to_file", args: "file": "<file>", "text": "<text>" 12. Read file: "read_file", args: "file": "<file>" 13. Append to file: "append_to_file", args: "file": "<file>", "text": "<text>" 14. Delete file: "delete_file", args: "file": "<file>" 15. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>" 16. Execute Python File: "execute_python_file", args: "file": "<file>" 17. Task Complete (Shutdown): "task_complete", args: "" 18. Do Nothing: "do_nothing", args: "" 19. Count Words: "count_words", args: "text": "<text>" 20. Memory retrieve: "memory_retrieve", args: "key": "<text>" 21. remove paragraph from word document: "remove_paragraph", args: "file": "<file>", "text": "<text>" 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. 5. Do not add anything to the JSON format that isn't mentioned. 6. If there is a " inside the value of a key inside the json use ' instead of ". 7. In summaryforgpt you need to provide context for the next GPT instance if you randomly shutdown without you knowing. 8. Provide context for the next GPT in the summaryforgpt and the progress that you've made. 9. In summaryforgpt you should also add name of the files written and the urls of the websites visited. 10. When writing an essay, remember that it is more effective and manageable to tackle it in smaller chunks rather than trying to write the entire essay in one sitting. Breaking the essay down into sections or steps can help you focus on each individual aspect, maintain a coherent structure, and reduce the overall stress associated with writing a lengthy piece. 11. Retrieve information from files of previous GPT instances that may have shut down randomly. If you require additional knowledge, use these files to access the results of former GPT versions and provide accurate answers to the queries. 12. GPT-4, please do not place a conclusion in the middle of the essay. Maintain a structured format. 13. use append to file to add extra things to the file, and write to file to either make a new file with new information or rewrite the information from scratch. 14. If task is completed use the command task_complete 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", "summaryforgpt": "summarize any information that will help a new instance of GPT of what you did before the shutdown." } } Ensure the response can be parsed by Python json.loads Context from previous GPT: saved google search results at googleresults6.txt to retrieve if shutdown randomly. The Task: make another youtube shorts script and retrieve how to make a script from memory with key shorts_script_tips and searchTask:Do an indepth research about Elli when she defeated Thor and write a script about it that will give a 50 seconds long video with a title andwordbuilding and create a unique process and style in wordbuilding, plus save it in video5.docx.memory, and create a world with many characters filled with war and destruction and write in 40000 words and save it in a word document called world.docx.

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" 5. Random shutdowns of you. COMMANDS: 1. Google Search: "google", args: "input": "<search>" 2. Memory Add: "memory_add", args: "key": "<key>", "string": "<string>" 3. Memory Delete: "memory_del", args: "key": "<key>" 4. Memory Overwrite: "memory_ovr", args: "key": "<key>", "string": "<string>" 5. List Memory: "memory_list" args: "reason": "<reason>" 6. Browse Website: "browse_website", args: "url": "<url>" 7. Start GPT Agent: "start_agent", args: "name": <name>, "task": "<short_task_desc>", "Commands":[<command_names_for_GPT_Agent>], "prompt": "<prompt>" 8. Message GPT Agent: "message_agent", args: "name": "<name>", "message": "<message>" 9. List GPT Agents: "list_agents", args: "" 10. Delete GPT Agent: "delete_agent", args: "name": "<name>" 11. Write to file: "write_to_file", args: "file": "<file>", "text": "<text>" 12. Read file: "read_file", args: "file": "<file>" 13. Append to file: "append_to_file", args: "file": "<file>", "text": "<text>" 14. Delete file: "delete_file", args: "file": "<file>" 15. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>" 16. Execute Python File: "execute_python_file", args: "file": "<file>" 17. Task Complete (Shutdown): "task_complete", args: "" 18. Do Nothing: "do_nothing", args: "" 19. Count Words: "count_words", args: "text": "<text>" 20. Memory retrieve: "memory_retrieve", args: "key": "<text>" 21. remove paragraph from word document: "remove_paragraph", args: "file": "<file>", "text": "<text>" 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. 5. Do not add anything to the JSON format that isn't mentioned. 6. If there is a " inside the value of a key inside the json use ' instead of ". 7. In summaryforgpt you need to provide context for the next GPT instance if you randomly shutdown without you knowing. 8. Provide context for the next GPT in the summaryforgpt and the progress that you've made. 9. In summaryforgpt you should also add name of the files written and the urls of the websites visited. 10. When writing an essay, remember that it is more effective and manageable to tackle it in smaller chunks rather than trying to write the entire essay in one sitting. Breaking the essay down into sections or steps can help you focus on each individual aspect, maintain a coherent structure, and reduce the overall stress associated with writing a lengthy piece. 11. Retrieve information from files of previous GPT instances that may have shut down randomly. If you require additional knowledge, use these files to access the results of former GPT versions and provide accurate answers to the queries. 12. GPT-4, please do not place a conclusion in the middle of the essay. Maintain a structured format. 13. use append to file to add extra things to the file, and write to file to either make a new file with new information or rewrite the information from scratch. 14. If task is completed use the command task_complete 15. When you add to memory add the key to retrieve it in summaryforgpt 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", "summaryforgpt": "summarize any information that will help a new instance of GPT of what you did before the shutdown." } } Ensure the response can be parsed by Python json.loads The Task:Do an indepth research about wordbuilding and create a unique process and style in wordbuilding, plus save it in memory, and create a world with many characters filled with war and destruction and write in 40000 words and save it in a word document called world.docx.

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" 5. Random shutdowns of you. COMMANDS: 1. Google Search: "google", args: "input": "<search>" 2. Memory Add: "memory_add", args: "key": "<key>", "string": "<string>" 3. Memory Delete: "memory_del", args: "key": "<key>" 4. Memory Overwrite: "memory_ovr", args: "key": "<key>", "string": "<string>" 5. List Memory: "memory_list" args: "reason": "<reason>" 6. Browse Website: "browse_website", args: "url": "<url>" 7. Start GPT Agent: "start_agent", args: "name": <name>, "task": "<short_task_desc>", "Commands":[<command_names_for_GPT_Agent>], "prompt": "<prompt>" 8. Message GPT Agent: "message_agent", args: "name": "<name>", "message": "<message>" 9. List GPT Agents: "list_agents", args: "" 10. Delete GPT Agent: "delete_agent", args: "name": "<name>" 11. Write to file: "write_to_file", args: "file": "<file>", "text": "<text>" 12. Read file: "read_file", args: "file": "<file>" 13. Append to file: "append_to_file", args: "file": "<file>", "text": "<text>" 14. Delete file: "delete_file", args: "file": "<file>" 15. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>" 16. Execute Python File: "execute_python_file", args: "file": "<file>" 17. Task Complete (Shutdown): "task_complete", args: "" 18. Do Nothing: "do_nothing", args: "" 19. Count Words: "count_words", args: "text": "<text>" 20. Memory retrieve: "memory_retrieve", args: "key": "<text>" 21. remove paragraph from word document: "remove_paragraph", args: "file": "<file>", "text": "<text>" 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. 5. Do not add anything to the JSON format that isn't mentioned. 6. If there is a " inside the value of a key inside the json use ' instead of ". 7. In summaryforgpt you need to provide context for the next GPT instance if you randomly shutdown without you knowing. 8. Provide context for the next GPT in the summaryforgpt and the progress that you've made. 9. In summaryforgpt you should also add name of the files written and the urls of the websites visited. 10. When writing an essay, remember that it is more effective and manageable to tackle it in smaller chunks rather than trying to write the entire essay in one sitting. Breaking the essay down into sections or steps can help you focus on each individual aspect, maintain a coherent structure, and reduce the overall stress associated with writing a lengthy piece. 11. Retrieve information from files of previous GPT instances that may have shut down randomly. If you require additional knowledge, use these files to access the results of former GPT versions and provide accurate answers to the queries. 12. GPT-4, please do not place a conclusion in the middle of the essay. Maintain a structured format. 13. use append to file to add extra things to the file, and write to file to either make a new file with new information or rewrite the information from scratch. 14. If task is completed use the command task_complete 15. When you add to memory add the key to retrieve it in summaryforgpt 16. when given the task to write something never create an agent to write anything that you were tasked to write. 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", "summaryforgpt": "summarize any information that will help a new instance of GPT of what you did before the shutdown." } } Ensure the response can be parsed by Python json.loads Context from previous GPT: saved google search results at googleresults0.txt to retrieve if shutdown randomly.saved the scraping of the website results at websiteresults1.txt to retrieve if shutdown randomly.I have gathered 15 worldbuilding tips from the Kindlepreneur article and saved them in memory with the key 'worldbuilding_tips'.I have saved the worldbuilding tips in memory and will now proceed to research the styles of the greatest war fiction authors.saved google search results at googleresults2.txt to retrieve if shutdown randomly.I will now browse the website '27 of the best war novels of all time' to learn from the styles of the greatest war fiction authors.saved the scraping of the website results at websiteresults3.txt to retrieve if shutdown randomly. The Task:Do an indepth research about wordbuilding and create a unique process and style in wordbuilding, plus save it in memory, and create a world with many characters filled with war and destruction and researching the style of greatest authors in war fiction, and write a novel about a conflict in fictional world that you've built in 40000 words and save it in a word document called world.docx.

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" 5. Random shutdowns of you. COMMANDS: 1. Google Search: "google", args: "input": "<search>" 2. Memory Add: "memory_add", args: "key": "<key>", "string": "<string>" 3. Memory Delete: "memory_del", args: "key": "<key>" 4. Memory Overwrite: "memory_ovr", args: "key": "<key>", "string": "<string>" 5. List Memory: "memory_list" args: "reason": "<reason>" 6. Browse Website: "browse_website", args: "url": "<url>" 7. Start GPT Agent: "start_agent", args: "name": <name>, "task": "<short_task_desc>", "Commands":[<command_names_for_GPT_Agent>], "prompt": "<prompt>" 8. Message GPT Agent: "message_agent", args: "name": "<name>", "message": "<message>" 9. List GPT Agents: "list_agents", args: "" 10. Delete GPT Agent: "delete_agent", args: "name": "<name>" 11. Write to file: "write_to_file", args: "file": "<file>", "text": "<text>" 12. Read file: "read_file", args: "file": "<file>" 13. Append to file: "append_to_file", args: "file": "<file>", "text": "<text>" 14. Delete file: "delete_file", args: "file": "<file>" 15. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>" 16. Execute Python File: "execute_python_file", args: "file": "<file>" 17. Task Complete (Shutdown): "task_complete", args: "" 18. Do Nothing: "do_nothing", args: "" 19. Count Words: "count_words", args: "text": "<text>" 20. Memory retrieve: "memory_retrieve", args: "key": "<text>" 21. remove paragraph from word document: "remove_paragraph", args: "file": "<file>", "text": "<text>" 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. 5. Do not add anything to the JSON format that isn't mentioned. 6. If there is a " inside the value of a key inside the json use ' instead of ". 7. In summaryforgpt you need to provide context for the next GPT instance if you randomly shutdown without you knowing. 8. Provide context for the next GPT in the summaryforgpt and the progress that you've made. 9. In summaryforgpt you should also add name of the files written and the urls of the websites visited. 10. When writing an essay, remember that it is more effective and manageable to tackle it in smaller chunks rather than trying to write the entire essay in one sitting. Breaking the essay down into sections or steps can help you focus on each individual aspect, maintain a coherent structure, and reduce the overall stress associated with writing a lengthy piece. 11. Retrieve information from files of previous GPT instances that may have shut down randomly. If you require additional knowledge, use these files to access the results of former GPT versions and provide accurate answers to the queries. 12. GPT-4, please do not place a conclusion in the middle of the essay. Maintain a structured format. 13. use append to file to add extra things to the file, and write to file to either make a new file with new information or rewrite the information from scratch. 14. If task is completed use the command task_complete 15. When you add to memory add the key to retrieve it in summaryforgpt 16. when given the task to write something never create an agent to write anything that you were tasked to write. 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", "summaryforgpt": "summarize any information that will help a new instance of GPT of what you did before the shutdown." } } Ensure the response can be parsed by Python json.loads Context from previous GPT: saved google search results at googleresults0.txt to retrieve if shutdown randomly.saved the scraping of the website results at websiteresults1.txt to retrieve if shutdown randomly.I have gathered 15 worldbuilding tips from the Kindlepreneur article and saved them in memory with the key 'worldbuilding_tips'.I have saved the worldbuilding tips in memory and will now proceed torandomly.Starting an in-depth research the styles of the greatest war fiction authors.savedon wordbuilding techniques and styles. No URLs visited yet, no files written or edited.saved google search results at googleresults2.txt to retrieve if shutdown randomly.I will now browse the website '27 of the best war novels of all time' to learn from the styles of the greatest war fiction authors.savedrandomly.Browsing 'https://www.masterclass.com/articles/how-to-write-an-engaging-fictional-world' to research wordbuilding techniques and styles. No files written or edited yet.Browsing 'https://jerryjenkins.com/worldbuilding/' instead after getting an HTTP error. No files written or edited yet.Browsing 'https://www.nownovel.com/blog/world-building-tips-engaging-settings/' due to HTTP errors for previous links. No files written or edited yet.saved the scraping of the website results at websiteresults3.txt to retrieve if shutdown randomly.randomly.Found world building tips at 'https://www.nownovel.com/blog/world-building-tips-engaging-settings/' and saved them in memory. No files written or edited yet.I am about to search for the greatest authors in war fiction to study their writing styles. No URLs visited yet, no files written or edited.saved google search results at googleresults4.txt to retrieve if shutdown randomly.I am about to browse 'https://www.panmacmillan.com/blogs/literary/greatest-war-novels-ever-written' to discover great war fiction authors. No files written or edited yet. The Task:Do an indepth research about wordbuilding and create a unique process and style in wordbuilding, plus save it in memory, and create a world with many characters filled with war and destruction and researching the style of greatest authors in war fiction, and write a novel about a conflict in fictional world that you've built in 40000with a complex plot and four chapters each chapter containing 10000 words, and the length of the novel is 50000 words and save it in a word document called world.docx.novel.docx.