Explore visual deep dives on machine learning papers, systems, and ideas.
Join the community on Discord →Choose your client to see the exact setup. Connect once, then ask naturally for any topic or paper.
An interactive series you work through: predict, play, derive and break things, from Dyna to every trick inside DreamerV3, ending with a world mode...
Picture someone wearing head mounted camera glasses in a kitchen. They pick up a kettle from the counter, turn around to face a cup behind them, an...
Imagine asking an AI assistant: “Find the decision in our project notes, check when the team is free, and create a follow up task.” To a person, th...
Type hello, world! into an LLM. To you, that string is already meaningful: two familiar words, a comma, a space, and an exclamation mark. To the ne...
Take a simple completion: “Alice gave Bob the book because wanted it.” Suppose the model assigns a high target logit $y$ to the correct next token....
A robot is about to push a puck across a table. There is a target marked a little farther away, and beyond it, the edge. A gentle push might leave ...
Suppose you want to train a model with a matrix optimizer such as Muon. The optimizer does not think of a weight matrix as a bag of independent num...
A plugin registers commands, subscribes to events, allocates resources, and changes shared state. Loading is easy because the host can start execut...
Imagine an LLM solving a math problem. It samples a full reasoning trace, you run a verifier, and the verifier returns a number: perhaps 0 for a co...
Imagine training a robot arm from a replay buffer that contains plenty of examples of ordinary motions—move left, move right, lower the gripper—but...
A diagram-rich generated explanation from the public library.
A diagram-rich generated explanation from the public library.
