Knowledge Base: AI, it's not that complicated
You'll learn: How to understand and work effectively with AI and ML models and products.
Knowledge Base information is split up into 4 sections, organized by how it important it is to know each bit; peruse at your own leisure.
Pro tip: bookmark any post by clicking the bookmark icon on the right, and you'll be able to see it in your account's reading list.
The Basics
Core concepts everyone should understand about AI and ML
What you need to know
- What are Large Language Models actually doing under the hood?
- A language-based ML model named GPT-3 took the world by storm.
What's nice to know
- Most data teams use a special type of code notebook to explore data and build AI models.
- How do you train an AI model? It all starts with data, and lots of it.
The Generative AI wave
How generative AI models get built and run
What you need to know
- 🔜 What is GenAI, exactly? Get a look at how models like ChatGPT and Stable Diffusion work under the hood.
What you should know
- Retrieval Augmented Generation is a way to make AI models more personalized.
- A Vector Database is a place where developers store specially formatted data to use for machine learning and AI.
What's nice to know
- Though all the rage, benchmarks are a one sided and inefficient way to measure AI model performance.
- 🔜 Newer GenAI models are developing the capability to think and reason instead of just generating words.
Tools and products
- How to build apps with AI (all about Vercel's v0).
Tools and Products
Key AI tools and platforms
Tools and products
- How various LLMs like Gemini and ChatGPT stack up when it comes to routine tasks.
- There are lots of AI products beyond OpenAI and ChatGPT.
- OpenAI is the most popular provider of generative AI models like GPT-4 and DALL-E.
- Databricks is a tool for running Spark jobs, basically ETL for big data.
- Browserbase lets AI models use the internet.