Topic

LLM

A large language model predicts the next token, over and over, using patterns learned from enormous amounts of text. Everything else, from chat to reasoning, is built on that loop. The guide here follows a prompt through tokens, embeddings, attention and the final prediction, so you can see where a model's strengths and its mistakes come from.

1 guide on LLM.

Reference Guide · 18 min read

How LLMs Work

Every stage a prompt passes through, modeled as an explorable 3D machine. 21 stages, a 21-step guided journey tracing one token from "The cat sat on the" to "mat", real parameter counts from GPT-3 to DeepSeek-V3, and the training story, pretraining, RLHF, and the reasoning-RL breakthrough.

LLM Transformers Attention Mixture of Experts Reasoning Models 3D Interactive AI Explainer

Keep learning LLM

A Helping Hand for LLMs (Retrieval Augmented Generation) - Computerphile video · Computerphile
AI & Text to SQL: How LLMs & Schema Power Data Analytics video · IBM Technology
AI Tool Calling via Natural Language: LLMs, APIs & Docker in Action video · IBM Technology
Faster LLMs: Accelerate Inference with Speculative Decoding video · IBM Technology
How KV Cache Speeds Up LLMs for Faster AI Models on GPUs video · IBM Technology
Is Fine-Tuning Still Needed? LLMs, RAG, & LoRA video · IBM Technology
Karpathy · Deep Dive into LLMs like ChatGPT (3h31m) video · Andrej Karpathy
LLM Compression Explained: Build Faster, Efficient AI Models video · IBM Technology

From the AI Roadmap. Every link was checked.

3D Interactive AI Explainer Attention Mixture of Experts Reasoning Models Transformers

All Guides

LLM

How LLMs Work

Keep learning LLM

Related topics