Skip to content
anythingai.space
new268 illustrated lessons · 141 guide chapters

AI systems, illustrated.

Learn how production AI really works — tokens, attention, RAG, agents, inference, evals — by stepping through animated diagrams. Every idea is a picture that moves, breaks and gets fixed in front of you.

25
modules
2409
animated steps
free
no login
Retrieval & RAG / RAG Fundamentals
question“Refunds are available within 60 days.”(actual policy: 14 days)UserLLMguessing
step 1 / 8
The model has never seen your data
How a lesson works

Every lesson tells the same five-part story.

Use ← → to step. Metrics update as the system changes, so you see what each decision buys you.

  1. Problem01

    Something breaks or doesn't scale.

  2. Key idea02

    The one insight that fixes it.

  3. How it works03

    Watch the mechanism move.

  4. Trade-off04

    What it costs, when it fails.

  5. Recap05

    The decision table to keep.

The course

Pick a module

All 25 modules
tokenize“I LOVE THIS PRODUCT!” → TOKENS (WITH A 2-D SLICE OF EACH EMBEDDING)I[0.1, 0.4]love[0.9, 0.8]this[0.2, 0.1]product[0.5, 0.3]![0.6, 0.7]Same pipeline, different heads: translate · classify · answer · summarise ·generateReview textEmbeddingstoken → vectorTransformerreads in contextPositivesentiment 0.9601

AI Foundations

Machine learning, deep learning, NLP, computer vision, reinforcement learning and the techniques underneath modern AI.

34 lessons427 min0/34
ENCODER · SEES EVERYTHINGThecatsatonmatThecatsatonmatDECODER · SEES ONLY THE PASTThecatsatonmatThecatsatonmatBERT-style → intent, sentiment,embedding modelsGPT-style → text generation, chat,agents02

How LLMs Work

Tokens, attention, transformers, embeddings and the inference pipeline — from text in to text out.

6 lessons74 min0/6
FRONTIERWORKHORSEFAST / EFFICIENTSMALL / EDGEFable 5.1$10 / $50GPT-6 Astra$10 / $50Opus 5.5$4 / $20Sonnet 5.5$2 / $10GPT-6.1 Sol$2 / $10GPT-6.1 Terra$1 / $5GPT-6 Luna$0.10 / $0.50Haiku 5.5$0.10 / $0.50 <100KGemini 3.8 Flash$0.75 / $3.75 introGemma 4 12BApache 2.0Qwen3.8-27BApache 2.0 · denseGranite 4.23B / 8B · Apache03

Choosing Models

The model landscape, capability assessment, pricing, and how to pick the right model for the job.

4 lessons49 min0/4
FSDP / ZERO: STATE SHARDED ACROSS GPUSPER PARAMETER ≈ 16 BYTES (TYPICAL SPLIT)BF16 weights · 2 BBF16 gradients · 2 BFP32 master copy · 4 BAdam momentum · 4 BAdam variance · 4 BGPU 11/4 of the stateGPU 21/4 of the stateGPU 31/4 of the stateGPU 41/4 of the state04

Training & Adaptation

Pretraining, fine-tuning, LoRA, RLHF/DPO, distillation, synthetic data, quantization and reasoning models.

8 lessons103 min0/8
COMPUTE PER BYTE OF MEMORY BANDWIDTHH100 · BF16~300 FLOPs/byteVera Rubin · NVFP4~2,600 FLOPs/byteH100: ~1 PFLOPS dense BF16 ÷ 3.35 TB/sHBM3Rubin: ~50 PFLOPS NVFP4 ÷ 19.2 TB/s HBM4Decode reads the weights once per step — so batch many sequences(or verify several speculative tokens) to use the compute you paidfor05

Inference & Serving

KV cache, batching, speculative decoding, paged attention, serving stacks and the cost playbook.

9 lessons112 min0/9
CONSISTENCY AS A SYSTEM PROPERTYtemperature=0Effort is the dial now,not sampling.Eval harnesstemperature: 0Model APIversion 2026-10-21400Pin model+effortSchema / enumInput-hash cachePass rateN runs per case06

Prompting & Context

Prompt fundamentals, few-shot, chain/tree of thought, context engineering, structured output and injection defense.

8 lessons90 min0/8
More ways in

Read, map, or follow a path.