Study library

Learn by building.

You leave able to implement ML from first principles, turn a paper into running code, and operate a long-context agent stack that is fast, cheap, and safe across tenants.

Today

Your progress

Stored only in this browser.

0%
0 of 0 done0%

Problems

200 hands-on ML implementations

200 pages

Research Papers

Implement landmark papers from scratch

172 pages

ML Math

67 interactive math chapters

67 pages

LLM Internals

How modern LLMs actually work

7 pages

CS/AI 684

Efficient Long-Context Agent Systems (14 weeks)

20 pages

Tensor→Tenant

108-week apprenticeship · 548 Darbar slots · 36-week on-ramp

716 pages

Guides

Writing & method

1 page