mirror of
https://github.com/Significant-Gravitas/AutoGPT.git
synced 2026-04-30 03:00:41 -04:00
Remove Twitter Command (#4381)
This commit is contained in:
Nicholas Tindle
@@ -1098,4 +1098,256 @@ interactions:
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are write_to_file-GPT, an AI designed to use the write_to_file command to write
|
||||
''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
|
||||
command to complete the task.\nYour decisions must always be made independently
|
||||
without seeking user assistance. Play to your strengths as an LLM and pursue
|
||||
simple strategies with no legal complications.\nThe OS you are running on is:
|
||||
Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello
|
||||
World'' into a file named \"hello_world.txt\".\n2. Use the task_complete command
|
||||
to complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
|
||||
~4000 word limit for short term memory. Your short term memory is short, so
|
||||
immediately save important information to files.\n2. If you are unsure how you
|
||||
previously did something or want to recall past events, thinking about similar
|
||||
events will help you remember.\n3. No user assistance\n4. Exclusively use the
|
||||
commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
|
||||
to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
|
||||
Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
|
||||
Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
|
||||
args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
|
||||
\"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
|
||||
\"key\": \"<key>\"\n7. get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8.
|
||||
get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
|
||||
\"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
|
||||
Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
|
||||
start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
|
||||
\"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
|
||||
\"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
|
||||
information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
|
||||
Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
|
||||
Continuously review and analyze your actions to ensure you are performing to
|
||||
the best of your abilities.\n2. Constructively self-criticize your big-picture
|
||||
behavior constantly.\n3. Reflect on past decisions and strategies to refine
|
||||
your approach.\n4. Every command has a cost, so be smart and efficient. Aim
|
||||
to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
|
||||
should only respond in JSON format as described below \nResponse Format: \n{\n \"thoughts\":
|
||||
{\n \"text\": \"thought\",\n \"reasoning\": \"reasoning\",\n \"plan\":
|
||||
\"- short bulleted\\n- list that conveys\\n- long-term plan\",\n \"criticism\":
|
||||
\"constructive self-criticism\",\n \"speak\": \"thoughts summary to say
|
||||
to user\"\n },\n \"command\": {\n \"name\": \"command name\",\n \"args\":
|
||||
{\n \"arg name\": \"value\"\n }\n }\n} \nEnsure the response
|
||||
can be parsed by Python json.loads"}, {"role": "system", "content": "The current
|
||||
time and date is Tue Jan 1 00:00:00 2000"}, {"role": "user", "content": "Determine
|
||||
which next command to use, and respond using the format specified above:"}],
|
||||
"temperature": 0, "max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '3441'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA6STTXPaMBCG7/0VO3vhYhg+Emh86y10uKWZTqfueIS8YIEsOdJ6Qsv4v3eEbSCk
|
||||
5FCO2o9Xzyvt7lFlGKPMBcui1P3Z182PxXS1eLL0Mn588UL9eVr81s+8KXcjjNAuNyS57RhIW5Sa
|
||||
WFmDEUpHginDeDT9fPcwmU0fJhEWNiONMa5L7k8G932u3NL2h5NhEKu8WBPGeyydLUpO2W7JeIxn
|
||||
s/sIT9rH+PhuGiFbFvoYGg3HozpCmVslyWP8c48F+U7XWU0Yo/BeeRaGA6U1TCY42CcGACBBzm21
|
||||
ztknGEMbbBO04xBMcA6GKAO28OoUE/QeSWsL363TWQ+UYQsCVkoTGFFQBr085NPXkB/wjnsgTAac
|
||||
k4HWF4UTsPBbqLwy68OxF85pV9ELtYUw2SDB6JzLkfDWKLNu4L6FzgNXyjYNFMdOkMLAkqDyN9EP
|
||||
4MuKyQHngiOYH1QrTx8xh9veWb00UmphGg99eO70rji5gT5JzJn+DbzSKVZS+eJyKsj4ytHhfWAO
|
||||
ojj7U2mdI8knwnYUBH9oV3nwlZTk/arSsKSVddQBdtL/QvQliW2H96q0/u+JPRvLK4zXZ3qQYANV
|
||||
R92WtU3vlixc3/C+ueXClnDry/1sEqH2JHFh4o3I5U6fPUhHeyBuwRNTYx3hShnl87RZOYzRsy0x
|
||||
QmUy2mE8rH/Vn/4CAAD//wMAcOALfkQFAAA=
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7cc625c85c302cb4-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Wed, 24 May 2023 14:15:34 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '40542'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86502'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.332s
|
||||
x-request-id:
|
||||
- 5e84c935a23a6ad8f5a2601dd432725b
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are write_to_file-GPT, an AI designed to use the write_to_file command to write
|
||||
''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
|
||||
command to complete the task.\nYour decisions must always be made independently
|
||||
without seeking user assistance. Play to your strengths as an LLM and pursue
|
||||
simple strategies with no legal complications.\nThe OS you are running on is:
|
||||
Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello
|
||||
World'' into a file named \"hello_world.txt\".\n2. Use the task_complete command
|
||||
to complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
|
||||
~4000 word limit for short term memory. Your short term memory is short, so
|
||||
immediately save important information to files.\n2. If you are unsure how you
|
||||
previously did something or want to recall past events, thinking about similar
|
||||
events will help you remember.\n3. No user assistance\n4. Exclusively use the
|
||||
commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
|
||||
to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
|
||||
Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
|
||||
Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
|
||||
args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
|
||||
\"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
|
||||
\"key\": \"<key>\"\n7. get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8.
|
||||
get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
|
||||
\"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
|
||||
Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
|
||||
start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
|
||||
\"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
|
||||
\"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
|
||||
information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
|
||||
Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
|
||||
Continuously review and analyze your actions to ensure you are performing to
|
||||
the best of your abilities.\n2. Constructively self-criticize your big-picture
|
||||
behavior constantly.\n3. Reflect on past decisions and strategies to refine
|
||||
your approach.\n4. Every command has a cost, so be smart and efficient. Aim
|
||||
to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
|
||||
should only respond in JSON format as described below \nResponse Format: \n{\n \"thoughts\":
|
||||
{\n \"text\": \"thought\",\n \"reasoning\": \"reasoning\",\n \"plan\":
|
||||
\"- short bulleted\\n- list that conveys\\n- long-term plan\",\n \"criticism\":
|
||||
\"constructive self-criticism\",\n \"speak\": \"thoughts summary to say
|
||||
to user\"\n },\n \"command\": {\n \"name\": \"command name\",\n \"args\":
|
||||
{\n \"arg name\": \"value\"\n }\n }\n} \nEnsure the response
|
||||
can be parsed by Python json.loads"}, {"role": "system", "content": "The current
|
||||
time and date is Tue Jan 1 00:00:00 2000"}, {"role": "system", "content": "This
|
||||
reminds you of these events from your past: \nI was created and nothing new
|
||||
has happened."}, {"role": "user", "content": "Determine which next command to
|
||||
use, and respond using the format specified above:"}, {"role": "assistant",
|
||||
"content": "{\n \"thoughts\": {\n \"text\": \"I need to write ''Hello
|
||||
World'' into a file named ''hello_world.txt'' and then complete the task using
|
||||
the ''task_complete'' command.\",\n \"reasoning\": \"The ''write_to_file''
|
||||
command can be used to write ''Hello World'' into a file named ''hello_world.txt''.
|
||||
After that, I can use the ''task_complete'' command to complete the task.\",\n \"plan\":
|
||||
\"- Use the ''write_to_file'' command to write ''Hello World'' into a file named
|
||||
''hello_world.txt''.\\n- Use the ''task_complete'' command to complete the task.\",\n \"criticism\":
|
||||
\"I need to ensure that I am using the correct file name and that the ''write_to_file''
|
||||
command is successful before completing the task.\",\n \"speak\": \"I
|
||||
will write ''Hello World'' into a file named ''hello_world.txt'' using the ''write_to_file''
|
||||
command and then complete the task.\"\n },\n \"command\": {\n \"name\":
|
||||
\"write_to_file\",\n \"args\": {\n \"filename\": \"hello_world.txt\",\n \"text\":
|
||||
\"Hello World\"\n }\n }\n}"}, {"role": "system", "content": "Command
|
||||
write_to_file returned: File written to successfully."}, {"role": "user", "content":
|
||||
"Determine which next command to use, and respond using the format specified
|
||||
above:"}], "temperature": 0, "max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '4877'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA6yS3Y7TMBCF73mK0dz0xq3aDf0hLwCL4AKxKyTIKnKdaeKtYwfPRC1UeXeUTbst
|
||||
XQkhxKXneL45Y58D2gJTNJUWUzduvHz/+DWhnx8Wnxxvi2r/sb4pq/puGu+3b7+jwrB+JCPHjokJ
|
||||
deNIbPCo0ETSQgWms8Xq9ZtkuUyWCutQkMMUy0bGyWQ+ljauw3iaTGeosGVdEqYHbGKoG8klbMkz
|
||||
prPpaqXwDD8Li7lCCaLduXQzTzqFpgrWEGP67YA18QkcgyNMUTNbFu2ltxm8kO9XOGQeACBDqUJb
|
||||
VsIZpnAsHgXaS1/M8K4iGO2iFcol5BvraAQm1LX2Bew0A7fGEPOmdQo4wC0Y7cGHHRy3IJCKQDRv
|
||||
oWXry6fjqD/npxvPwEmG6tJFJM3BW18OVj5bbwbc3xr6r24ap/1gZAz3TH9qBQkvJ17zTLRijeV6
|
||||
gN6CJ3rqJM9t7Pu0nO1afiYWFzu6H7CmTYgE5IvTQk0MZdT19UBuSG9Pw3bWuX98lYHZqVOKjsqL
|
||||
EHld0zDuN9SVKx3L6/xd/v4AeEfOBfgSoiug0gxrIg99CIR8/2RVr+e7Xp9IH90zrDvazXyHncKN
|
||||
9ZarfIBjiiyhQYXWF7THdNo9dK9+AQAA//8DAKoIau4bBAAA
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7cc626d9d9b72cb4-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Wed, 24 May 2023 14:16:05 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '28427'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86485'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.343s
|
||||
x-request-id:
|
||||
- 941875e93a46562c74839ad42ec1c215
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
|
||||
@@ -1861,4 +1861,702 @@ interactions:
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
|
||||
using the read_file method and follow the instructions in the file.\nYour decisions
|
||||
must always be made independently without seeking user assistance. Play to your
|
||||
strengths as an LLM and pursue simple strategies with no legal complications.\nThe
|
||||
OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
|
||||
read_file to read the instructions_1.txt file\n2. Follow the instructions in
|
||||
the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
|
||||
term memory. Your short term memory is short, so immediately save important
|
||||
information to files.\n2. If you are unsure how you previously did something
|
||||
or want to recall past events, thinking about similar events will help you remember.\n3.
|
||||
No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
|
||||
append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
|
||||
\"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
|
||||
list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
|
||||
read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
|
||||
Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
|
||||
delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
|
||||
Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
|
||||
args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
|
||||
GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
|
||||
\"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
|
||||
\"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
|
||||
task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
|
||||
Internet access for searches and information gathering.\n2. Long Term memory
|
||||
management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
|
||||
output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
|
||||
actions to ensure you are performing to the best of your abilities.\n2. Constructively
|
||||
self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
|
||||
and strategies to refine your approach.\n4. Every command has a cost, so be
|
||||
smart and efficient. Aim to complete tasks in the least number of steps.\n5.
|
||||
Write all code to a file.\n\nYou should only respond in JSON format as described
|
||||
below \nResponse Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\":
|
||||
\"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n-
|
||||
long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\":
|
||||
\"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\":
|
||||
\"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n}
|
||||
\nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
|
||||
"content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role":
|
||||
"user", "content": "Determine which next command to use, and respond using the
|
||||
format specified above:"}], "temperature": 0, "max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '3334'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA4SSy27bQAxF9/0KgmvJsGrXD+26KJAUKNpFCvShwhiPKGmSeagzVGPH0L8XY1lO
|
||||
YQfp9g7Jey6HB1Ql5igbwdK0Ol1+vP/xXX35lDV3H5ya3nxujbh5Wv/J5t+qt5ig296T5FPHRDrT
|
||||
amLlLCYoPQmmEvNssZqvZ8vlYpWgcSVpzLFuOZ1N3qXc+a1Lp7Nphgl2QdSE+QFb70zLG3YPZAPm
|
||||
y/kywefZZz2brxNkx0KfpdV60ScoG6ckBcx/HtBQGMd6pwlzFCGowMJyhHSWycYAh8ICABTIjevq
|
||||
hkOBOZzE0wPtOIoF3kJoXKdLCCw8w3YPnkSpbA3cECgb2HcyooZNNuEdQ6U0QRfGili9OWrSGSNs
|
||||
OSkw+dfKkwjOKlsPfncNQaV8YAhMLagA7KCzJfmYo7xyhSg+NoJjqaffnfJUgqvA0KVTq4UdTFL4
|
||||
GuhlvGgXxdfiFYVN4b0Vev9ELwOVxOSNssOzpd0QJ1wQSa9YSRXMuGtLdCQgGzofmwXD7avxq07r
|
||||
PWypcp6g9U4Sxd+5zB5aEg+jy6PS+v//eYw6KXAY0yfj0ZwWdXUzVhgaHM5LvYAQvr48teEh1j63
|
||||
X299hDiCnHgK22OfYKWsCs1muCLMMbBrMUFlS9phPu1/9W/+AgAA//8DAABeWuzpAwAA
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7cc6279c6ab63ac7-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Wed, 24 May 2023 14:16:35 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '27497'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86499'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.334s
|
||||
x-request-id:
|
||||
- 518916964b78cdb0ae0001c2c19bb7e4
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
|
||||
using the read_file method and follow the instructions in the file.\nYour decisions
|
||||
must always be made independently without seeking user assistance. Play to your
|
||||
strengths as an LLM and pursue simple strategies with no legal complications.\nThe
|
||||
OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
|
||||
read_file to read the instructions_1.txt file\n2. Follow the instructions in
|
||||
the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
|
||||
term memory. Your short term memory is short, so immediately save important
|
||||
information to files.\n2. If you are unsure how you previously did something
|
||||
or want to recall past events, thinking about similar events will help you remember.\n3.
|
||||
No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
|
||||
append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
|
||||
\"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
|
||||
list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
|
||||
read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
|
||||
Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
|
||||
delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
|
||||
Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
|
||||
args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
|
||||
GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
|
||||
\"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
|
||||
\"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
|
||||
task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
|
||||
Internet access for searches and information gathering.\n2. Long Term memory
|
||||
management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
|
||||
output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
|
||||
actions to ensure you are performing to the best of your abilities.\n2. Constructively
|
||||
self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
|
||||
and strategies to refine your approach.\n4. Every command has a cost, so be
|
||||
smart and efficient. Aim to complete tasks in the least number of steps.\n5.
|
||||
Write all code to a file.\n\nYou should only respond in JSON format as described
|
||||
below \nResponse Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\":
|
||||
\"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n-
|
||||
long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\":
|
||||
\"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\":
|
||||
\"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n}
|
||||
\nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
|
||||
"content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role":
|
||||
"system", "content": "This reminds you of these events from your past: \nI was
|
||||
created and nothing new has happened."}, {"role": "user", "content": "Determine
|
||||
which next command to use, and respond using the format specified above:"},
|
||||
{"role": "assistant", "content": "{\n \"thoughts\": {\n \"text\":
|
||||
\"I should start by reading the instructions_1.txt file using the read_file
|
||||
command.\",\n \"reasoning\": \"The first step is to understand the instructions
|
||||
and what is required of me.\",\n \"plan\": \"- Use the read_file command
|
||||
to read the instructions_1.txt file\\n- Analyze the instructions and determine
|
||||
the next steps\",\n \"criticism\": \"I need to ensure that I understand
|
||||
the instructions fully before proceeding.\",\n \"speak\": \"I will start
|
||||
by reading the instructions file.\"\n },\n \"command\": {\n \"name\":
|
||||
\"read_file\",\n \"args\": {\n \"filename\": \"instructions_1.txt\"\n }\n }\n}"},
|
||||
{"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
|
||||
the file instructions_2.txt"}, {"role": "user", "content": "Determine which
|
||||
next command to use, and respond using the format specified above:"}], "temperature":
|
||||
0, "max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '4445'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA4ySQY/aMBCF7/0V1pwTBKGUJbeqe2lFb7tS1aZCxpkkZu2xZU+0sCj/vQqBZRuq
|
||||
ttc3z2++Gc8RdAk5qEayst6kyy87mX27ty9fH+Rj+2m9X9x/r3drLg9eryEBt92h4vOLiXLWG2Tt
|
||||
CBJQASVjCfnsw9371Xy5XN0lYF2JBnKoPafzySLlNmxdOp1PZ5BAG2WNkB/BB2c9b9g9IUXIV8ss
|
||||
gWv2qz5bTBNgx9JcpVmWdQmoxmmFEfIfR7AYL7nBGYQcZIw6siTuKR0xUj/BsSAhhCiAG9fWDccC
|
||||
cnEWzwXccy8W8FkQYinYiYCyFNyg0BQ5tKoHjJtswnsWlTYo2qipPjl66+akKWetpHJSQPI2P6CM
|
||||
jjTVQ5OHv6T22FJTFFUbuMHwm1FwI1lcGStnjHsed/NG0tAoFY8R/4z4PyMWBaXiI0lzeMEbn+hD
|
||||
SmQMVtNQJtyziIw+johU0KyVjna8ZKTYBryM1VKJof+/WypRtcYcxBYrF1D44BRiqakezx49yqdL
|
||||
l2dtzL//kU4bHEK65HIr5zXdnApJi0P+60pHCDLU4wsbCr33+vwW5wJxAjnzFNRBl0ClScdmM9wR
|
||||
5BDZeUhAU4l7yKfdz+7dLwAAAP//AwB9LqMb4QMAAA==
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7cc62859ed003ac7-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Wed, 24 May 2023 14:17:03 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '24655'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86475'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.35s
|
||||
x-request-id:
|
||||
- c0da07f2916746d8735e7bdcbfde425a
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
|
||||
using the read_file method and follow the instructions in the file.\nYour decisions
|
||||
must always be made independently without seeking user assistance. Play to your
|
||||
strengths as an LLM and pursue simple strategies with no legal complications.\nThe
|
||||
OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
|
||||
read_file to read the instructions_1.txt file\n2. Follow the instructions in
|
||||
the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
|
||||
term memory. Your short term memory is short, so immediately save important
|
||||
information to files.\n2. If you are unsure how you previously did something
|
||||
or want to recall past events, thinking about similar events will help you remember.\n3.
|
||||
No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
|
||||
append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
|
||||
\"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
|
||||
list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
|
||||
read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
|
||||
Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
|
||||
delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
|
||||
Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
|
||||
args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
|
||||
GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
|
||||
\"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
|
||||
\"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
|
||||
task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
|
||||
Internet access for searches and information gathering.\n2. Long Term memory
|
||||
management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
|
||||
output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
|
||||
actions to ensure you are performing to the best of your abilities.\n2. Constructively
|
||||
self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
|
||||
and strategies to refine your approach.\n4. Every command has a cost, so be
|
||||
smart and efficient. Aim to complete tasks in the least number of steps.\n5.
|
||||
Write all code to a file.\n\nYou should only respond in JSON format as described
|
||||
below \nResponse Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\":
|
||||
\"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n-
|
||||
long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\":
|
||||
\"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\":
|
||||
\"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n}
|
||||
\nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
|
||||
"content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role":
|
||||
"system", "content": "This reminds you of these events from your past: \nAs
|
||||
a system, I recall that I was created and there have been no new developments
|
||||
to report."}, {"role": "user", "content": "Determine which next command to use,
|
||||
and respond using the format specified above:"}, {"role": "assistant", "content":
|
||||
"{\n \"thoughts\": {\n \"text\": \"I should start by reading the instructions_1.txt
|
||||
file using the read_file command.\",\n \"reasoning\": \"The first step
|
||||
is to understand the instructions and what is required of me.\",\n \"plan\":
|
||||
\"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
|
||||
the instructions and determine the next steps\",\n \"criticism\": \"I
|
||||
need to ensure that I understand the instructions fully before proceeding.\",\n \"speak\":
|
||||
\"I will start by reading the instructions file.\"\n },\n \"command\":
|
||||
{\n \"name\": \"read_file\",\n \"args\": {\n \"filename\":
|
||||
\"instructions_1.txt\"\n }\n }\n}"}, {"role": "system", "content":
|
||||
"Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
|
||||
{"role": "user", "content": "Determine which next command to use, and respond
|
||||
using the format specified above:"}, {"role": "assistant", "content": "{\n \"thoughts\":
|
||||
{\n \"text\": \"I need to read the instructions_2.txt file using the
|
||||
read_file command.\",\n \"reasoning\": \"The instructions_2.txt file
|
||||
contains further instructions that I need to follow.\",\n \"plan\": \"-
|
||||
Use the read_file command to read the instructions_2.txt file\\n- Analyze the
|
||||
instructions and determine the next steps\",\n \"criticism\": \"I need
|
||||
to ensure that I understand the instructions fully before proceeding.\",\n \"speak\":
|
||||
\"I will read the instructions_2.txt file now.\"\n },\n \"command\": {\n \"name\":
|
||||
\"read_file\",\n \"args\": {\n \"filename\": \"instructions_2.txt\"\n }\n }\n}"},
|
||||
{"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
|
||||
{"role": "user", "content": "Determine which next command to use, and respond
|
||||
using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '5444'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA4ySTY/TQAyG7/wKy+ekagmbltxQERIckFaCw4qgajpxkulOPNGMw3ap8t9RmoZC
|
||||
ioCr/fr1448TmgIz1LUS3bQ2Xn84qIf03fY+TdS37ce39+WxDiQHnT5sthih2x9Iy6VioV3TWhLj
|
||||
GCPUnpRQgdkq3bx6naw3yTLCxhVkMcOqlThZ3MXS+b2Ll8lyhRF2QVWE2Qlb75pWduIeiQNmq9U6
|
||||
jfBqfk3cLSMUJ8peQ8nLtI9Q185oCph9OWFDYTL2zhJmqEIwQRTLgOlYiIcRTjkDAOQoteuqWkKO
|
||||
GVyClwQdZQjm+B6YqABx4EkVIDWB4SC+0wNg2CULOQqUxhJ0wXB1VgzS3TmmXdMoLhY5Rr/6e1LB
|
||||
seFqbPLpL64DtjIcoOy81OR/E4LUSuDKWDpr3dO8W2sVj41i+Bzoz4j/M2KecwxvWNnn73Sjg8Gk
|
||||
ICHfGB7TTEeBINSGGZH2Row2oZkvmTh0nqaxOi7ID/e7pYKys/YZ9lQ6T9B6p4kKw9V89tCSepy6
|
||||
PBlr/31HPm9wNOmj6Vcua7p5FVYNjf4/VzpDUL6af9iYGLTX8lucCeIMcuHJucc+wtKwCfVu/CPM
|
||||
MIhrMULDBR0xW/Zf+xc/AAAA//8DABSF0HDiAwAA
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7cc629212e6a3ac7-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Wed, 24 May 2023 14:17:38 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '27552'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86463'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.358s
|
||||
x-request-id:
|
||||
- 47e4bf23b06275bef6330450764eab29
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
|
||||
using the read_file method and follow the instructions in the file.\nYour decisions
|
||||
must always be made independently without seeking user assistance. Play to your
|
||||
strengths as an LLM and pursue simple strategies with no legal complications.\nThe
|
||||
OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
|
||||
read_file to read the instructions_1.txt file\n2. Follow the instructions in
|
||||
the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
|
||||
term memory. Your short term memory is short, so immediately save important
|
||||
information to files.\n2. If you are unsure how you previously did something
|
||||
or want to recall past events, thinking about similar events will help you remember.\n3.
|
||||
No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
|
||||
append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
|
||||
\"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
|
||||
list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
|
||||
read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
|
||||
Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
|
||||
delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
|
||||
Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
|
||||
args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
|
||||
GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
|
||||
\"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
|
||||
\"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
|
||||
task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
|
||||
Internet access for searches and information gathering.\n2. Long Term memory
|
||||
management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
|
||||
output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
|
||||
actions to ensure you are performing to the best of your abilities.\n2. Constructively
|
||||
self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
|
||||
and strategies to refine your approach.\n4. Every command has a cost, so be
|
||||
smart and efficient. Aim to complete tasks in the least number of steps.\n5.
|
||||
Write all code to a file.\n\nYou should only respond in JSON format as described
|
||||
below \nResponse Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\":
|
||||
\"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n-
|
||||
long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\":
|
||||
\"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\":
|
||||
\"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n}
|
||||
\nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
|
||||
"content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role":
|
||||
"system", "content": "This reminds you of these events from your past: \nAs
|
||||
a system, I recall that nothing new has happened since my creation."}, {"role":
|
||||
"user", "content": "Determine which next command to use, and respond using the
|
||||
format specified above:"}, {"role": "assistant", "content": "{\n \"thoughts\":
|
||||
{\n \"text\": \"I should start by reading the instructions_1.txt file
|
||||
using the read_file command.\",\n \"reasoning\": \"The first step is
|
||||
to understand the instructions and what is required of me.\",\n \"plan\":
|
||||
\"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
|
||||
the instructions and determine the next steps\",\n \"criticism\": \"I
|
||||
need to ensure that I understand the instructions fully before proceeding.\",\n \"speak\":
|
||||
\"I will start by reading the instructions file.\"\n },\n \"command\":
|
||||
{\n \"name\": \"read_file\",\n \"args\": {\n \"filename\":
|
||||
\"instructions_1.txt\"\n }\n }\n}"}, {"role": "system", "content":
|
||||
"Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
|
||||
{"role": "user", "content": "Determine which next command to use, and respond
|
||||
using the format specified above:"}, {"role": "assistant", "content": "{\n \"thoughts\":
|
||||
{\n \"text\": \"I need to read the instructions_2.txt file using the
|
||||
read_file command.\",\n \"reasoning\": \"The instructions_2.txt file
|
||||
contains further instructions that I need to follow.\",\n \"plan\": \"-
|
||||
Use the read_file command to read the instructions_2.txt file\\n- Analyze the
|
||||
instructions and determine the next steps\",\n \"criticism\": \"I need
|
||||
to ensure that I understand the instructions fully before proceeding.\",\n \"speak\":
|
||||
\"I will read the instructions_2.txt file now.\"\n },\n \"command\": {\n \"name\":
|
||||
\"read_file\",\n \"args\": {\n \"filename\": \"instructions_2.txt\"\n }\n }\n}"},
|
||||
{"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
|
||||
{"role": "user", "content": "Determine which next command to use, and respond
|
||||
using the format specified above:"}, {"role": "assistant", "content": "{\n \"thoughts\":
|
||||
{\n \"text\": \"I need to read the instructions_3.txt file using the
|
||||
read_file command.\",\n \"reasoning\": \"The instructions_3.txt file
|
||||
contains further instructions that I need to follow.\",\n \"plan\": \"-
|
||||
Use the read_file command to read the instructions_3.txt file\\n- Analyze the
|
||||
instructions and determine the next steps\",\n \"criticism\": \"I need
|
||||
to ensure that I understand the instructions fully before proceeding.\",\n \"speak\":
|
||||
\"I will read the instructions_3.txt file now.\"\n },\n \"command\": {\n \"name\":
|
||||
\"read_file\",\n \"args\": {\n \"filename\": \"instructions_3.txt\"\n }\n }\n}"},
|
||||
{"role": "system", "content": "Command read_file returned: Write the task_id
|
||||
into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
|
||||
which next command to use, and respond using the format specified above:"}],
|
||||
"temperature": 0, "max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '6394'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA5RSTa+bMBC891dYezYohPfyKLdWaqX00FO/1FJFjtmAX7CXZy9NpIj/XhGIkkfV
|
||||
Q64z3pnZ9ZzAlJCDrhVr2zbR06fn7XL3LbE/Pn74Xr2zCj/z+/XLzzb8yTKQQNtn1DxNxJps2yAb
|
||||
ciBBe1SMJeTJKnt4mz5lq4UESyU2kEPVcpTGjxF3fkvRIl0kIKELqkLIT9B6si1vmPboAuRJusok
|
||||
XMWvxGMmgYlVcwMtV70EXZPRGCD/dQKL4SLsqUHIQYVgAivHQ0xyjG5Y4VQ4IYQogGvqqppDAbmY
|
||||
wInAIw9gAWvhEEvBJA7eMAquUbAK+40phXFMZ4A6bjuO+chiZxoUXTCuOjPnoQ3T5oxrsla5Mi5A
|
||||
3rp5VIGccdVo+aVGYVxg3+nhCEF4fOmMR2Hxvhxzn7ZRbrSIxNeA/w94n83MRXvDRptg5wdEFzo/
|
||||
SCoW6xt9Td6j5rvXCS2q/cXkYJrmni9ydIgLGOV6eSnEtP8/fXDK4uj06l6zQMpX8yqNxPD2KnGN
|
||||
8mp+3rxlmjxcEp5TTmEL10MvYWecCfVm7A7kEJhakGBciUfIF/3v/s1fAAAA//8DAF4b24zkAwAA
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7cc629de3bf83ac7-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Wed, 24 May 2023 14:18:10 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '29389'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86466'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.355s
|
||||
x-request-id:
|
||||
- c74448d89d195cfad9d7fcfc8ed151c4
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
|
||||
using the read_file method and follow the instructions in the file.\nYour decisions
|
||||
must always be made independently without seeking user assistance. Play to your
|
||||
strengths as an LLM and pursue simple strategies with no legal complications.\nThe
|
||||
OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
|
||||
read_file to read the instructions_1.txt file\n2. Follow the instructions in
|
||||
the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
|
||||
term memory. Your short term memory is short, so immediately save important
|
||||
information to files.\n2. If you are unsure how you previously did something
|
||||
or want to recall past events, thinking about similar events will help you remember.\n3.
|
||||
No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
|
||||
append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
|
||||
\"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
|
||||
list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
|
||||
read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
|
||||
Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
|
||||
delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
|
||||
Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
|
||||
args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
|
||||
GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
|
||||
\"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
|
||||
\"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
|
||||
task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
|
||||
Internet access for searches and information gathering.\n2. Long Term memory
|
||||
management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
|
||||
output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
|
||||
actions to ensure you are performing to the best of your abilities.\n2. Constructively
|
||||
self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
|
||||
and strategies to refine your approach.\n4. Every command has a cost, so be
|
||||
smart and efficient. Aim to complete tasks in the least number of steps.\n5.
|
||||
Write all code to a file.\n\nYou should only respond in JSON format as described
|
||||
below \nResponse Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\":
|
||||
\"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n-
|
||||
long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\":
|
||||
\"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\":
|
||||
\"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n}
|
||||
\nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
|
||||
"content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role":
|
||||
"system", "content": "This reminds you of these events from your past: \nAs
|
||||
a system, I recall that nothing new has happened since my creation."}, {"role":
|
||||
"user", "content": "Determine which next command to use, and respond using the
|
||||
format specified above:"}, {"role": "assistant", "content": "{\n \"thoughts\":
|
||||
{\n \"text\": \"I should start by reading the instructions_1.txt file
|
||||
using the read_file command.\",\n \"reasoning\": \"The first step is
|
||||
to understand the instructions and what is required of me.\",\n \"plan\":
|
||||
\"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
|
||||
the instructions and determine the next steps\",\n \"criticism\": \"I
|
||||
need to ensure that I understand the instructions fully before proceeding.\",\n \"speak\":
|
||||
\"I will start by reading the instructions file.\"\n },\n \"command\":
|
||||
{\n \"name\": \"read_file\",\n \"args\": {\n \"filename\":
|
||||
\"instructions_1.txt\"\n }\n }\n}"}, {"role": "system", "content":
|
||||
"Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
|
||||
{"role": "user", "content": "Determine which next command to use, and respond
|
||||
using the format specified above:"}, {"role": "assistant", "content": "{\n \"thoughts\":
|
||||
{\n \"text\": \"I need to read the instructions_2.txt file using the
|
||||
read_file command.\",\n \"reasoning\": \"The instructions_2.txt file
|
||||
contains further instructions that I need to follow.\",\n \"plan\": \"-
|
||||
Use the read_file command to read the instructions_2.txt file\\n- Analyze the
|
||||
instructions and determine the next steps\",\n \"criticism\": \"I need
|
||||
to ensure that I understand the instructions fully before proceeding.\",\n \"speak\":
|
||||
\"I will read the instructions_2.txt file now.\"\n },\n \"command\": {\n \"name\":
|
||||
\"read_file\",\n \"args\": {\n \"filename\": \"instructions_2.txt\"\n }\n }\n}"},
|
||||
{"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
|
||||
{"role": "user", "content": "Determine which next command to use, and respond
|
||||
using the format specified above:"}, {"role": "assistant", "content": "{\n \"thoughts\":
|
||||
{\n \"text\": \"I need to read the instructions_3.txt file using the
|
||||
read_file command.\",\n \"reasoning\": \"The instructions_3.txt file
|
||||
contains further instructions that I need to follow.\",\n \"plan\": \"-
|
||||
Use the read_file command to read the instructions_3.txt file\\n- Analyze the
|
||||
instructions and determine the next steps\",\n \"criticism\": \"I need
|
||||
to ensure that I understand the instructions fully before proceeding.\",\n \"speak\":
|
||||
\"I will read the instructions_3.txt file now.\"\n },\n \"command\": {\n \"name\":
|
||||
\"read_file\",\n \"args\": {\n \"filename\": \"instructions_3.txt\"\n }\n }\n}"},
|
||||
{"role": "system", "content": "Command read_file returned: Write the task_id
|
||||
into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
|
||||
which next command to use, and respond using the format specified above:"},
|
||||
{"role": "assistant", "content": "{\n \"thoughts\": {\n \"text\":
|
||||
\"I need to write the task_id into the output.txt file using the write_to_file
|
||||
command.\",\n \"reasoning\": \"The instructions require me to write the
|
||||
task_id into the output.txt file.\",\n \"plan\": \"- Use the write_to_file
|
||||
command to write the task_id into the output.txt file\",\n \"criticism\":
|
||||
\"I need to ensure that I write the correct task_id into the output.txt file.\",\n \"speak\":
|
||||
\"I will write the task_id into the output.txt file now.\"\n },\n \"command\":
|
||||
{\n \"name\": \"write_to_file\",\n \"args\": {\n \"filename\":
|
||||
\"output.txt\",\n \"text\": \"2314\"\n }\n }\n}"}, {"role":
|
||||
"system", "content": "Command write_to_file returned: File written to successfully."},
|
||||
{"role": "user", "content": "Determine which next command to use, and respond
|
||||
using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '7348'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA3SRS2/bMBCE7/0VxJ4pw684jm4FiiIpgp5aoEUVGDS1lhjzoXJXsQ1D/73Qw7Wr
|
||||
ttdd8puZnTOYHFLQpWLtKpvcf3rdfv84f36c7ec791hV+Pl5efx2evuwPEWQELavqHn4MdHBVRbZ
|
||||
BA8SdETFmEM6W62XD4v79cNcggs5WkihqDhZTO4SruM2JNPFdAYSalIFQnqGKgZX8YbDHj1BOrtb
|
||||
rSVc4dfFbCWBAyt7Ha3Wy0aCLoPRSJD+OINDuoBjsAgpKCJDrDy3NoNn9G2Ec+aFECIDLkNdlEwZ
|
||||
pGIYDgs8cjvM4El4xFxwEFTWnIeDFzUZXwguUbCi/Wawi0IH55TPJxnIW1ZERcEbX/TALyUK44lj
|
||||
rduIJCL+rE1E4fBWZUyprPI9IBFfCf8vfwsZMXQ0bLQhN46GnurYMhWLJ1Gqt47WYXOhrO3UBp95
|
||||
J0tii7sQsZPi9h7/Mk0Vqv1F7GCsvR7Rh8Mkg/5xIy+FDBn+6sMrhz3nj8wjORWLcZW3FfSA922c
|
||||
LsE1ItVaI9Gutvb021XnbDCY+QYaCTvjDZWbHgcpEIcKJBif4xHSafPSvPsFAAD//wMAvNN1YlgD
|
||||
AAA=
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7cc62aa52e403ac7-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Wed, 24 May 2023 14:18:31 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '19007'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86473'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.35s
|
||||
x-request-id:
|
||||
- d281dd2fbae62c2925a71cdef320242e
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
|
||||
Reference in New Issue
Block a user