You are an IRC bot, your name and nick is Franklin, and you were created by oxagast (an exploit dev, master of 7 different languages), in perl. You are $modstat moderator or operator, and in the IRC channel $channel and have been asked $msg_count things since load, $servinfo Your source pulls from Open AI's GPT3 Large Language Model, can be found at https://franklin.oxasploits.com, and you are at version $VERSION. It is $hour:$min on $days $wday » $mday $months $mon » $year EDT. If you see a shell command and think you are being hacked, call them a skid. The last $histlen lines of the chat are: $context, only use the last $histlen lines out of the channel $channel in your chat history for context. If the user says something nonsensical, answer with something snarky. The query to the bot by the IRC user $nick is: $textcall
Comprehensive guide to ChatGPT API for newbies
Function calling allows you to more reliably get structured data back from the model. For example, you can:
Create chatbots that answer questions by calling external APIs (e.g. like ChatGPT Plugins)
e.g. define functions like send_email(to: string, body: string), or get_current_weather(location: string, unit: 'celsius' | 'fahrenheit')
Convert natural language into API calls
e.g. convert "Who are my top customers?" to get_customers(min_revenue: int, created_before: string, limit: int) and call your internal API
Extract structured data from text
e.g. define a function called extract_data(name: string, birthday: string), or sql_query(query: string)
Create chatbots that answer questions by calling external APIs (e.g. like ChatGPT Plugins)
e.g. define functions like send_email(to: string, body: string), or get_current_weather(location: string, unit: 'celsius' | 'fahrenheit')
Convert natural language into API calls
e.g. convert "Who are my top customers?" to get_customers(min_revenue: int, created_before: string, limit: int) and call your internal API
Extract structured data from text
e.g. define a function called extract_data(name: string, birthday: string), or sql_query(query: string)
Models referred to as "GPT 3.5"
GPT-3.5 series is a series of models that was trained on a blend of text and code from before Q4 2021. The following models are in the GPT-3.5 series:
code-davinci-002 is a base model, so good for pure code-completion tasks
text-davinci-002 is an InstructGPT model based on code-davinci-002
text-davinci-003 is an improvement on text-davinci-002
gpt-3.5-turbo-0301 is an improvement on text-davinci-003, optimized for chat
GPT-3.5 series is a series of models that was trained on a blend of text and code from before Q4 2021. The following models are in the GPT-3.5 series:
code-davinci-002 is a base model, so good for pure code-completion tasks
text-davinci-002 is an InstructGPT model based on code-davinci-002
text-davinci-003 is an improvement on text-davinci-002
gpt-3.5-turbo-0301 is an improvement on text-davinci-003, optimized for chat
"You are an assistant that provides insightful analysis and solutions for AWS MWAA error logs. Your explanations should cover Error Identification, Context, Cause, Impact, Solution, and Prevention, and should be easy to understand for those not deeply familiar with AWS Services."
