// the find
ashishps1/learn-ai-engineering
Learn AI and LLMs from scratch using free resources
A curated list of free resources for learning AI/ML engineering, organized from math foundations through LLMs, RAG, agents, and MCP. It's essentially a structured bookmark dump for someone starting from zero or filling gaps in their knowledge. The target is developers who want a clear path through the noise rather than stumbling across courses randomly.
The organization is genuinely good — math → Python → ML → deep learning → LLMs → agents follows actual prerequisite dependencies rather than dumping everything alphabetically. The paper selection is solid: the Attention paper, BERT, GPT-3, and Chain-of-Thought are the ones that actually matter. Source diversity is real — Karpathy, fast.ai, Deeplearning.ai, Hugging Face, and Stanford courses each have different pedagogical strengths and the list doesn't just pick one. MCP coverage is recent and accurate, which is rare in lists that haven't been updated since 2023.
It's a list of links, not a learning path — there's no guidance on sequencing within sections or how long anything takes, so a beginner still has to figure out what to actually do first. The books section has a lot of Manning pre-release titles that may or may not be finished, mixed in with established O'Reilly references, with no distinction between them. No coverage of evals, observability, or prompt testing frameworks, which are the parts that actually bite you when you ship. Last updated February 2026 but already feels behind on reasoning models and newer agent frameworks — the pace of this field means lists like this have a half-life measured in months.