> For the complete documentation index, see [llms.txt](https://skillful-ai.gitbook.io/skillful-ai-public-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://skillful-ai.gitbook.io/skillful-ai-public-docs/links-and-glossary/glossary.md).

# Glossary

The terms are condensed down to be easily digestible, and some of the descriptions may be closer to anecdotes than literally meanings. The point is to allow non-technical users grasp concepts

## Web3 / Blockchain Terms: 

* **Non-Fungible** - Objects or assets that are all unique. The are distinguishable from one another 
* **NFT** (Non-fungible Token)\
  This is part of the underlying technology that makes up the digital asset you will come to know as the "Personal Assistants". It is a special way of keeping the information that allows every digital asset to be unique from one another. It is more than just the "Picture" you see on the marketplace.

## AI & Tech Stack Terms: 

* **Few-shot** - A prompt method where u give the LLM background info so that it has a better chance at answering a new question
* **Zero-Shot** - Just question input, without context or attempts made beforehand.
* **LLM(s)** - Large language model(s)
* **CoT** - Chain of thought prompting. \
  *Some papers to expand on it* [*1*](https://ai.googleblog.com/2022/05/language-models-perform-reasoning-via.html#:~:text=Chain%20of%20thought%20prompting%20is%20a%20simple%20and,prompting%20is%20an%20emergent%20property%20of%20model%20scale.) [*2*](https://arxiv.org/pdf/2201.11903.pdf) 
* **NLP** - Natural language processing
* **ANN/NN** - [Artificial neural network](https://en.wikipedia.org/wiki/Artificial_neural_network)
* **Knowledge Distillation** - The process of training a "smaller model" off of a larger model to allow for accurate responses while only accessing a smaller amount of data [1.](https://en.wikipedia.org/wiki/Knowledge_distillation)
* **Model Parameters / Trainable Parameters** - sum of all the weights and biases on the neural network