Topic

AI Explainer

3 guides tagged AI Explainer. Reference guides written to be the resource people and answer engines cite.

Reference Guide · 17 min read

What is Jev

Jev, released by TypeSafe AI on 2026-09-15, decides instead of writing. 14 stations across 4 kinds of responsibility, a 12-step guided journey from a ticket to a routed queue and on into an agent harness, the three answer shapes (Choice, Score, Noul) as working instruments, pricing and context limits from the vendor's own pages, and two independent preprints on where it fails. Sources checked 2026-09-24.

Jev TypeSafe AI System One model AI Agents Classification Structured Outputs 3D Interactive AI Explainer

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

Reference Guide · 20 min read

How Neural Networks Work

The canonical 784-16-16-10 MNIST network as an explorable 3D machine: 16 stations across 4 acts, a 16-step guided journey from pixels to the brain question, all 12,960 weight connections really drawn, and a training row where gradient descent is really computed on an illustrative loss terrain, and a Train mode where the network genuinely learns 10,000 real MNIST digits in your browser.

Neural Networks Deep Learning Backpropagation Gradient Descent MNIST 3D Interactive AI Explainer

All Guides