Please enable JavaScript.
Coggle requires JavaScript to display documents.
Prompt engineering part 2 - Coggle Diagram
Prompt engineering part 2
Key concepts of terminology
Artificial intelligence : when a machine is able to mimic human intelligence by having the ability to predict , classify , learn , plan , reason and / or perceive
input / output
input : the information or data given to an Ai system
output : the response or result generated by the Ai system
Natural language processing: subset of Ai that helps systems to drive meaning and undderstanding from language
prompt engineering definition: a set of instructions or a question given to Ai to elicit a response
machine learning : a subset of Ai that incorporates math and statistics in order to learn from the data itself , and improve with experience
Key concepts and terminology
Machine learning
A Definition : a subset of Ai focused on building systems that learn from data
Example : facial recognition, product recommendations, email automation and spam filtering , social media optimization , and mobile voice to text and predictive text
Ai model
Definition : A computational framework or system trained to perform tasks that typically require human intelligence , such as understanding language or recognizing patterns
Example : chatgpt , which generates human like text based on the prompts given
Natural Language processing
Definition : a field of ai that focuses on the interaction between computers and humans through natural language . it enables computers to understand , interpret , and respond to human language
Example : language translations services like google translate
How AI model understands prompts
The magic of NLP : Al models rely on field called Natural language processing to understand the instructions we give them ' just like humans use language skills to comprehend each other
How NLP breaks down our prompts :
step 1 : tokenization - breaking down the sentence
what it is :tokenization is like taking a sentence and splitting into individual words or smaller units called " tokens "
Example : for the prompt " write a poem about a cat " the Ai breaks it down into tokens : " write ", "a" , "poem " , " about " , "a" , " cat " .
step 2 : parsing - understanding the structure
What it is : parsing is like diagramming a sentence in grammar class . The Ai analyzes how these token " words " relate to each other ,, identifying parts of speech and the overall structure of the sentence
Example : in the sentence , " write " is the verb , "a" , is an article that modifies both " poem " and "cat " , and " poem " is the object of the verb " write "
step 3 : context is key - grasping the meaning
what it is : at the Ai goes beyond the literal meaning of the words and considers the broader context of the prompt , including previous interactions and the overall tasks