Gen-AI Developer Classroom notes 25/Mar/2025

AI

• Artificial General Intellingence is field where we have systems which behave like humans
• AI (Narrow AI) is field where we have system which thinks like human in a specific domain
• Narrow AI became popular with a subfield of AI called as Machine Learning. ML can predict or classify or clustering all based of mathematical/statistical models
• Deep Learning is a subfield of ML where the statistical models were designed based on Neural Networks(inspired from human brain) to perform complex tasks.
• LLMs are sub field of Deep Learning.
  

Differentiate between ML Model and Generative AI Model

• Generative AI Model takes input and produces the output which is
  • text
  • code
  • image
  • video
  • audio

• ML Model takes input and produces the output which is either a prediction or a classification

• Input to the LLM is called as prompt and the generated output is called as completion
  
  

Accounts

• GitHub
• gmail
• hugging face
• OpenAI
• Anthropic
• Mistral
• Grok
• Cloud:
  • Azure
  • GCP
  • AWS

Tokens

• Prompt gets broken into multiple tokens
• LLM models have token limits and pricing is based on tokens
  

Prompts influence completions

• Since Promepts influence completions (generated output), we need to know different approaches for better prompting.
• For this we have two fields
  • Prompt design
  • Prompt Engineering