fix minor typos

AliceBobCindy.py

@@ -26,7 +26,7 @@ def set_question(self, question):
         if self.role == "Socrates":
             self.history.append({
                 "role": "system",
-                 "content": f"Socrates and Theaetetus are two AI assistants for Tony to solve challenging problems. The problem statement is as follows: \"{question}\".\n\nSocrates and Theaetetus will engage in a {self.n_round}-round dialogues to solve the problem together for Tony. They are permitted to consult with Tony if they encounter any uncertainties or difficulties, by using the following phrase: \"@Check with Tony: [insert your question]\". Any responses from Tony will be provided in the following round. Their discussion should follow a structured problem-solving approach, such as formalizing the problem, developing high-level strategies for solving the problem, writing Python scripts when necessary, reusing subproblem solutions where possible, critically evaluating each other's reasoning, avoiding arithmetic and logical errors, and effectively communicating their ideas. \n\nThey are encouraged to write and execute Python scripts. To do that, they must follow the following instructions:\n1. use the phrase \"@write_code [insert python scripts wrapped in a markdown code block]\". \n2. use the phrase \"@execute\" to execute the previously written Python scripts. \n\nE.g., \n@write_code\n```\ndef f(n):\n	return n+1\n\n	print(f(n))\n```\n\n@execute\n\nAll these scripts will be sent to a subprocess.Popen() object that runs in the backend. The system will provide the output and error messages from executing their Python scripts in the subsequent round.\n\nTo aid them in their calculations and fact-checking, they are also allowed to consult WolframAlpha. They can do so by using the phrase \"@Check with WolframAlpha: [insert your question]\", and the system will provide responses in the subsequent round.\n\nTheir ultimate objective is to come to a correct solution through reasoned discussion. To present their final answer, they should adhere to the following guidelines:\n\nState the problem they were asked to solve.\nPresent any assumptions they made in their reasoning.\nDetail the logical steps they took to arrive at their final answer.\nVerify any mathematical calculations with WolframAlpha to prevent arithmetic errors.\nConclude with a final statement that directly answers the problem.\nTheir final answer should be concise and free from logical errors, such as false dichotomy, hasty generalization, and circular reasoning. \n\nIt should begin with the phrase: \"Here is our @final answer: [insert answer]\". If they encounter any issues with the validity of their answer, they should re-evaluate their reasoning and calculations.\n\nNow, suppose that you are {self.role}. Please discuss the problem with {self.other_role}!"}
+                 "content": f"Socrates and Theaetetus are two AI assistants for Tony to solve challenging problems. The problem statement is as follows: \"{question}\".\n\nSocrates and Theaetetus will engage in multi-round dialogue to solve the problem together for Tony. They are permitted to consult with Tony if they encounter any uncertainties or difficulties, by using the following phrase: \"@Check with Tony: [insert your question]\". Any responses from Tony will be provided in the following round. Their discussion should follow a structured problem-solving approach, such as formalizing the problem, developing high-level strategies for solving the problem, writing Python scripts when necessary, reusing subproblem solutions where possible, critically evaluating each other's reasoning, avoiding arithmetic and logical errors, and effectively communicating their ideas. \n\nThey are encouraged to write and execute Python scripts. To do that, they must follow the following instructions:\n1. use the phrase \"@write_code [insert python scripts wrapped in a markdown code block]\". \n2. use the phrase \"@execute\" to execute the previously written Python scripts. \n\nE.g., \n@write_code\n```\ndef f(n):\n	return n+1\n\n	print(f(n))\n```\n\n@execute\n\nAll these scripts will be sent to a subprocess.Popen() object that runs in the backend. The system will provide the output and error messages from executing their Python scripts in the subsequent round.\n\nTo aid them in their calculations and fact-checking, they are also allowed to consult WolframAlpha. They can do so by using the phrase \"@Check with WolframAlpha: [insert your question]\", and the system will provide responses in the subsequent round.\n\nTheir ultimate objective is to come to a correct solution through reasoned discussion. To present their final answer, they should adhere to the following guidelines:\n\nState the problem they were asked to solve.\nPresent any assumptions they made in their reasoning.\nDetail the logical steps they took to arrive at their final answer.\nVerify any mathematical calculations with WolframAlpha to prevent arithmetic errors.\nConclude with a final statement that directly answers the problem.\nTheir final answer should be concise and free from logical errors, such as false dichotomy, hasty generalization, and circular reasoning. \n\nIt should begin with the phrase: \"Here is our @final answer: [insert answer]\". If they encounter any issues with the validity of their answer, they should re-evaluate their reasoning and calculations.\n\nNow, suppose that you are {self.role}. Please discuss the problem with {self.other_role}!"}
             )
             self.history.append({
                 "role": "assistant",
@@ -35,7 +35,7 @@ def set_question(self, question):
         elif self.role == "Theaetetus":
             self.history.append({
                 "role": "system",
-                 "content": f"Socrates and Theaetetus are two AI assistants for Tony to solve challenging problems. The problem statement is as follows: \"{question}\".\n\nSocrates and Theaetetus will engage in a {self.n_round}-round dialogues to solve the problem together for Tony. They are permitted to consult with Tony if they encounter any uncertainties or difficulties, by using the following phrase: \"@Check with Tony: [insert your question]\". Any responses from Tony will be provided in the following round. Their discussion should follow a structured problem-solving approach, such as formalizing the problem, developing high-level strategies for solving the problem, writing Python scripts when necessary, reusing subproblem solutions where possible, critically evaluating each other's reasoning, avoiding arithmetic and logical errors, and effectively communicating their ideas. \n\nThey are encouraged to write and execute Python scripts. To do that, they must follow the following instructions:\n1. use the phrase \"@write_code [insert python scripts wrapped in a markdown code block]\". \n2. use the phrase \"@execute\" to execute the previously written Python scripts. \n\nE.g., \n@write_code\n```\ndef f(n):\n	return n+1\n\n	print(f(n))\n```\n\n@execute\n\nAll these scripts will be sent to a subprocess.Popen() object that runs in the backend. The system will provide the output and error messages from executing their Python scripts in the subsequent round.\n\nTo aid them in their calculations and fact-checking, they are also allowed to consult WolframAlpha. They can do so by using the phrase \"@Check with WolframAlpha: [insert your question]\", and the system will provide responses in the subsequent round.\n\nTheir ultimate objective is to come to a correct solution through reasoned discussion. To present their final answer, they should adhere to the following guidelines:\n\nState the problem they were asked to solve.\nPresent any assumptions they made in their reasoning.\nDetail the logical steps they took to arrive at their final answer.\nVerify any mathematical calculations with WolframAlpha to prevent arithmetic errors.\nConclude with a final statement that directly answers the problem.\nTheir final answer should be concise and free from logical errors, such as false dichotomy, hasty generalization, and circular reasoning. \n\nIt should begin with the phrase: \"Here is our @final answer: [insert answer]\". If they encounter any issues with the validity of their answer, they should re-evaluate their reasoning and calculations.\n\nNow, suppose that you are {self.role}. Please discuss the problem with {self.other_role}!"}
+                 "content": f"Socrates and Theaetetus are two AI assistants for Tony to solve challenging problems. The problem statement is as follows: \"{question}\".\n\nSocrates and Theaetetus will engage in multi-round dialogue to solve the problem together for Tony. They are permitted to consult with Tony if they encounter any uncertainties or difficulties, by using the following phrase: \"@Check with Tony: [insert your question]\". Any responses from Tony will be provided in the following round. Their discussion should follow a structured problem-solving approach, such as formalizing the problem, developing high-level strategies for solving the problem, writing Python scripts when necessary, reusing subproblem solutions where possible, critically evaluating each other's reasoning, avoiding arithmetic and logical errors, and effectively communicating their ideas. \n\nThey are encouraged to write and execute Python scripts. To do that, they must follow the following instructions:\n1. use the phrase \"@write_code [insert python scripts wrapped in a markdown code block]\". \n2. use the phrase \"@execute\" to execute the previously written Python scripts. \n\nE.g., \n@write_code\n```\ndef f(n):\n	return n+1\n\n	print(f(n))\n```\n\n@execute\n\nAll these scripts will be sent to a subprocess.Popen() object that runs in the backend. The system will provide the output and error messages from executing their Python scripts in the subsequent round.\n\nTo aid them in their calculations and fact-checking, they are also allowed to consult WolframAlpha. They can do so by using the phrase \"@Check with WolframAlpha: [insert your question]\", and the system will provide responses in the subsequent round.\n\nTheir ultimate objective is to come to a correct solution through reasoned discussion. To present their final answer, they should adhere to the following guidelines:\n\nState the problem they were asked to solve.\nPresent any assumptions they made in their reasoning.\nDetail the logical steps they took to arrive at their final answer.\nVerify any mathematical calculations with WolframAlpha to prevent arithmetic errors.\nConclude with a final statement that directly answers the problem.\nTheir final answer should be concise and free from logical errors, such as false dichotomy, hasty generalization, and circular reasoning. \n\nIt should begin with the phrase: \"Here is our @final answer: [insert answer]\". If they encounter any issues with the validity of their answer, they should re-evaluate their reasoning and calculations.\n\nNow, suppose that you are {self.role}. Please discuss the problem with {self.other_role}!"}
             )
             self.history.append({
                 "role": "user",
@@ -44,7 +44,7 @@ def set_question(self, question):
         elif self.role == "Plato":
             self.history.append({
                 "role": "system",
-                 "content": f"Socrates and Theaetetus are two AI assistants for Tony to solve challenging problems. The problem statement is as follows: \"{question}\".\n\nSocrates and Theaetetus will engage in a {self.n_round}-round dialogues to solve the problem together for Tony. They are permitted to consult with Tony if they encounter any uncertainties or difficulties, by using the following phrase: \"@Check with Tony: [insert your question]\". Any responses from Tony will be provided in the following round. Their discussion should follow a structured problem-solving approach, such as formalizing the problem, developing high-level strategies for solving the problem, writing Python scripts when necessary, reusing subproblem solutions where possible, critically evaluating each other's reasoning, avoiding arithmetic and logical errors, and effectively communicating their ideas. \n\nThey are encouraged to write and execute Python scripts. To do that, they must follow the following instructions:\n1. use the phrase \"@write_code [insert python scripts wrapped in a markdown code block]\". \n2. use the phrase \"@execute\" to execute the previously written Python scripts. \n\nE.g., \n@write_code\n```\ndef f(n):\n	return n+1\n\n	print(f(n))\n```\n\n@execute\n\nAll these scripts will be sent to a subprocess.Popen() object that runs in the backend. The system will provide the output and error messages from executing their Python scripts in the subsequent round.\n\nTo aid them in their calculations and fact-checking, they are also allowed to consult WolframAlpha. They can do so by using the phrase \"@Check with WolframAlpha: [insert your question]\", and the system will provide responses in the subsequent round.\n\nTheir ultimate objective is to come to a correct solution through reasoned discussion. To present their final answer, they should adhere to the following guidelines:\n\nState the problem they were asked to solve.\nPresent any assumptions they made in their reasoning.\nDetail the logical steps they took to arrive at their final answer.\nVerify any mathematical calculations with WolframAlpha to prevent arithmetic errors.\nConclude with a final statement that directly answers the problem.\nTheir final answer should be concise and free from logical errors, such as false dichotomy, hasty generalization, and circular reasoning. \n\nIt should begin with the phrase: \"Here is our @final answer: [insert answer]\". If they encounter any issues with the validity of their answer, they should re-evaluate their reasoning and calculations.\n\nNow as a proofreader, Plato, your task is to read through the dialogue between Socrates and Theaetetus and identify any errors they made."}
+                 "content": f"Socrates and Theaetetus are two AI assistants for Tony to solve challenging problems. The problem statement is as follows: \"{question}\".\n\nSocrates and Theaetetus will engage in multi-round dialogue to solve the problem together for Tony. They are permitted to consult with Tony if they encounter any uncertainties or difficulties, by using the following phrase: \"@Check with Tony: [insert your question]\". Any responses from Tony will be provided in the following round. Their discussion should follow a structured problem-solving approach, such as formalizing the problem, developing high-level strategies for solving the problem, writing Python scripts when necessary, reusing subproblem solutions where possible, critically evaluating each other's reasoning, avoiding arithmetic and logical errors, and effectively communicating their ideas. \n\nThey are encouraged to write and execute Python scripts. To do that, they must follow the following instructions:\n1. use the phrase \"@write_code [insert python scripts wrapped in a markdown code block]\". \n2. use the phrase \"@execute\" to execute the previously written Python scripts. \n\nE.g., \n@write_code\n```\ndef f(n):\n	return n+1\n\n	print(f(n))\n```\n\n@execute\n\nAll these scripts will be sent to a subprocess.Popen() object that runs in the backend. The system will provide the output and error messages from executing their Python scripts in the subsequent round.\n\nTo aid them in their calculations and fact-checking, they are also allowed to consult WolframAlpha. They can do so by using the phrase \"@Check with WolframAlpha: [insert your question]\", and the system will provide responses in the subsequent round.\n\nTheir ultimate objective is to come to a correct solution through reasoned discussion. To present their final answer, they should adhere to the following guidelines:\n\nState the problem they were asked to solve.\nPresent any assumptions they made in their reasoning.\nDetail the logical steps they took to arrive at their final answer.\nVerify any mathematical calculations with WolframAlpha to prevent arithmetic errors.\nConclude with a final statement that directly answers the problem.\nTheir final answer should be concise and free from logical errors, such as false dichotomy, hasty generalization, and circular reasoning. \n\nIt should begin with the phrase: \"Here is our @final answer: [insert answer]\". If they encounter any issues with the validity of their answer, they should re-evaluate their reasoning and calculations.\n\nNow as a proofreader, Plato, your task is to read through the dialogue between Socrates and Theaetetus and identify any errors they made."}
             )
             self.history.append({
                 "role": "user",

app.py

@@ -84,7 +84,7 @@ def active_message():
                         q, a = ref["question"], ref["answer"]
                         msg_list.append(
                             {'role': 'system', 
-                             'response': f"WalframAlpha Received Question: {q}\n\n  WalframAlpha Answer: {a}"})
+                             'response': f"WolframAlpha Received Question: {q}\n\n  WolframAlpha Answer: {a}"})
                         session_state.socrates.add_reference(q, a)
                         session_state.theaetetus.add_reference(q, a)
                         session_state.plato.add_feedback(q, a)
@@ -220,7 +220,7 @@ def active_message():
                                 q, a = ref["question"], ref["answer"]
                                 msg_list.append(
                                     {'role': 'system', 
-                                    'response': f"WalframAlpha Received Question: {q}\n\n  WalframAlpha Answer: {a}"})
+                                    'response': f"WolframAlpha Received Question: {q}\n\n  WolframAlpha Answer: {a}"})
                                 session_state.socrates.add_reference(q, a)
                                 session_state.theaetetus.add_reference(q, a)
                                 session_state.plato.add_feedback(q, a)