A visual AI learning roadmap: 3Blue1Brown, Transformer Explainer, Neuronpedia and more
techNmak · x · 2026-09-04
A complete visual-first roadmap for learning AI from scratch:
- Math: 3Blue1Brown → Seeing Theory
- ML: TensorFlow Playground → Distill
- Transformers: Jay Alammar → Transformer Explainer → Bycroft
- Modern LLMs: RoPE → GQA/MLA → MoE
- Inference: Modular; Embeddings: Embedding Atlas; Interpretability: Neuronpedia
Key advice: don't spend weeks watching 15 explanations of basic attention — once the canonical Transformer clicks, move on to RoPE, GQA/MLA, MoE, KV caching, FlashAttention, batching, quantization, speculative decoding and interpretability, where modern LLM engineering gets interesting.
Related event: Community curates interactive resources for learning AI visually(13 posts)→
More from coding & agent
- Free Design Skill for Lovable brings Linear-grade design systems to AI-built apps — damienghader · 2026-09-04
- Dev keeps forgetting he installed a Vegeta skill, gets delightful Dragon Ball replies — tekbog · 2026-09-04
- Claude Code vs Codex: one-shot migration takes 37 min with zero rework vs 27 min but broken twice — notherealironman · 2026-09-04
- Open source coding agent opencode passes 200k GitHub stars — anomalyco · 2026-09-04
- Post-mortem: why in-memory agent state graphs failed in 24/7 production, and the disk-backed fix — Remarkable_Plant7820 · 2026-09-04
- Ian Nuttall burns through all Ahrefs MCP credits in one week, falls back to computer use — iannuttall · 2026-09-04