AI is a set of tools
- Supervised learning (labeling things)
- Generative AI
- Unsupervised learning
- Reinforcement learning
Supervised learning (labeling things)
- Application
- Spam filtering
- Online advertising
- Self-driving car
- Healthcare
- Visual inspection
- Speech recognition
- 2010 -2020: Large scale supervised learning
- Large AI models vs Small AI models
Generating text using Large Language Models (LLMs)
- Text generation process
- prompt+AI output
How Large Language Models (LLMs) work
- LLMs are built by using supervised learning(A->B) to repeatedly predict the next word.
- one sentence is turned into multiple inputs A and outputs B for it to try to learn from where the LLM is learning,given a few words, to predict what is the next word that comes out there
- When we train a very large AI system on a lot of data ( hundreds of billions of words), we get a Large Language Model like ChatGPT.
- that's given a prompt, is very good at generating some additional words in response to that prompt
- they're trained to repeatedly predict the next word;