# @aartii.py on Instagram

- **Type:** Video
- **Original URL:** https://www.instagram.com/p/DdDeuZBv57q
- **Gondola URL:** https://gondola.cc/posts/70375083-aartiipy-instagram
- **Thumbnail:** https://img.gondola.cc/tr:w-,h-,fo-auto/postThumbnails/93411fc786.jpg
- **Posted:** 2026-09-09T05:13:13.000+00:00
- **Account Owner:** Aarti Sinha (@aartii.py) — https://gondola.cc/aartii.py

## Caption

Explanation of each term below->

LLM: predicts the next word, one at a time, based on everything before it. Scale that up and you get answers, code, and conversation from the same mechanism.

Tokenization: text becomes tokens before the model reads it, each one a word or a fragment of one. The model never sees individual letters, only these chunks.

Context window: how much the model can hold at once, measured in tokens. Anything past the edge does not exist to it.

Embeddings: turning text into numbers that carry meaning. Similar ideas end up close together, so you can compare meaning mathematically.

Vector database: storage built for those numbers, able to find the closest matches across millions of entries in milliseconds. It searches by meaning, not keywords.

Cosine similarity: the math behind “closest”. It compares the direction of two embeddings rather than their size.

RAG: the model does not know your documents, so you fetch the relevant ones first and hand them over with the question. Private data, no retraining.

MCP: a shared standard for connecting models to real tools and data. One interface instead of building a custom integration for every service.

Fine tuning: taking a general model and training it further on your specific task. It shapes how the model responds, not what facts it holds.

Overfitting: the model memorizes the training data instead of learning the pattern. Looks perfect in training, falls apart on anything new.

Knowledge distillation: a large model teaches a smaller one to imitate it. Most of the behaviour, a fraction of the cost to run.

#tech #ai #coding #programming #student

## Stats

- **Views:** 16,610
- **Likes:** 3
- **Shares:** 0
- **Comments:** 12

## Tags

programming, coding, ai, tech, student

---
Copyright (c) Gondola