Skip to content
Open
Show file tree
Hide file tree
Changes from 2 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions BACKERS.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
# Backers

Thank you to all our backers who support the development of this curriculum!

## Backers List
*(No backers listed yet)*
19 changes: 19 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -257,6 +257,7 @@ Twenty phases. Click any phase to expand its lesson list.
| 11 | [Linux for AI](phases/00-setup-and-tooling/11-linux-for-ai/) | Learn | — |
| 12 | [Debugging & Profiling](phases/00-setup-and-tooling/12-debugging-and-profiling/) | Build | Python |

<a id="phase-1"></a>
Comment thread
coderabbitai[bot] marked this conversation as resolved.
Outdated
<details id="phase-1">
<summary><b>Phase 1 — Math Foundations</b> &nbsp;<code>22 lessons</code>&nbsp; <em>The intuition behind every AI algorithm, through code.</em></summary>
<br/>
Expand Down Expand Up @@ -288,6 +289,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-2"></a>
<details id="phase-2">
<summary><b>Phase 2 — ML Fundamentals</b> &nbsp;<code>18 lessons</code>&nbsp; <em>Classical ML — still the backbone of most production AI.</em></summary>
<br/>
Expand Down Expand Up @@ -315,6 +317,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-3"></a>
<details id="phase-3">
<summary><b>Phase 3 — Deep Learning Core</b> &nbsp;<code>13 lessons</code>&nbsp; <em>Neural networks from first principles. No frameworks until you build one.</em></summary>
<br/>
Expand All @@ -337,6 +340,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-4"></a>
<details id="phase-4">
<summary><b>Phase 4 — Computer Vision</b> &nbsp;<code>28 lessons</code>&nbsp; <em>From pixels to understanding — image, video, 3D, VLMs, and world models.</em></summary>
<br/>
Expand Down Expand Up @@ -374,6 +378,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-5"></a>
<details id="phase-5">
<summary><b>Phase 5 — NLP: Foundations to Advanced</b> &nbsp;<code>29 lessons</code>&nbsp; <em>Language is the interface to intelligence.</em></summary>
<br/>
Expand Down Expand Up @@ -412,6 +417,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-6"></a>
<details id="phase-6">
<summary><b>Phase 6 — Speech & Audio</b> &nbsp;<code>17 lessons</code>&nbsp; <em>Hear, understand, speak.</em></summary>
<br/>
Expand All @@ -438,6 +444,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-7"></a>
<details id="phase-7">
<summary><b>Phase 7 — Transformers Deep Dive</b> &nbsp;<code>14 lessons</code>&nbsp; <em>The architecture that changed everything.</em></summary>
<br/>
Expand All @@ -461,6 +468,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-8"></a>
<details id="phase-8">
<summary><b>Phase 8 — Generative AI</b> &nbsp;<code>14 lessons</code>&nbsp; <em>Create images, video, audio, 3D, and more.</em></summary>
<br/>
Expand All @@ -484,6 +492,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-9"></a>
<details id="phase-9">
<summary><b>Phase 9 — Reinforcement Learning</b> &nbsp;<code>12 lessons</code>&nbsp; <em>The foundation of RLHF and game-playing AI.</em></summary>
<br/>
Expand All @@ -505,6 +514,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-10"></a>
<details id="phase-10">
<summary><b>Phase 10 — LLMs from Scratch</b> &nbsp;<code>22 lessons</code>&nbsp; <em>Build, train, and understand large language models.</em></summary>
<br/>
Expand Down Expand Up @@ -536,6 +546,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-11"></a>
<details id="phase-11">
<summary><b>Phase 11 — LLM Engineering</b> &nbsp;<code>17 lessons</code>&nbsp; <em>Put LLMs to work in production.</em></summary>
<br/>
Expand All @@ -562,6 +573,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-12"></a>
<details id="phase-12">
<summary><b>Phase 12 — Multimodal AI</b> &nbsp;<code>25 lessons</code>&nbsp; <em>See, hear, read, and reason across modalities — from ViT patches to computer-use agents.</em></summary>
<br/>
Expand Down Expand Up @@ -596,6 +608,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-13"></a>
<details id="phase-13">
<summary><b>Phase 13 — Tools & Protocols</b> &nbsp;<code>23 lessons</code>&nbsp; <em>The interfaces between AI and the real world.</em></summary>
<br/>
Expand Down Expand Up @@ -628,6 +641,7 @@ Twenty phases. Click any phase to expand its lesson list.

</details>

<a id="phase-14"></a>
<details id="phase-14">
<summary><b>Phase 14 — Agent Engineering</b> &nbsp;<code>42 lessons</code>&nbsp; <em>Build agents from first principles — loop, memory, planning, frameworks, benchmarks, production, workbench.</em></summary>
<br/>
Expand Down Expand Up @@ -681,6 +695,7 @@ Each Phase 14 workbench lesson (31-42) ships a `mission.md` briefing the agent b

</details>

<a id="phase-15"></a>
<details id="phase-15">
<summary><b>Phase 15 — Autonomous Systems</b> &nbsp;<code>22 lessons</code>&nbsp; <em>Long-horizon agents, self-improvement, and the 2026 safety stack.</em></summary>
<br/>
Expand Down Expand Up @@ -712,6 +727,7 @@ Each Phase 14 workbench lesson (31-42) ships a `mission.md` briefing the agent b

</details>

<a id="phase-16"></a>
<details id="phase-16">
<summary><b>Phase 16 — Multi-Agent & Swarms</b> &nbsp;<code>25 lessons</code>&nbsp; <em>Coordination, emergence, and collective intelligence.</em></summary>
<br/>
Expand Down Expand Up @@ -746,6 +762,7 @@ Each Phase 14 workbench lesson (31-42) ships a `mission.md` briefing the agent b

</details>

<a id="phase-17"></a>
<details id="phase-17">
<summary><b>Phase 17 — Infrastructure & Production</b> &nbsp;<code>28 lessons</code>&nbsp; <em>Ship AI to the real world.</em></summary>
<br/>
Expand Down Expand Up @@ -783,6 +800,7 @@ Each Phase 14 workbench lesson (31-42) ships a `mission.md` briefing the agent b

</details>

<a id="phase-18"></a>
<details id="phase-18">
<summary><b>Phase 18 — Ethics, Safety & Alignment</b> &nbsp;<code>30 lessons</code>&nbsp; <em>Build AI that helps humanity. Not optional.</em></summary>
<br/>
Expand Down Expand Up @@ -822,6 +840,7 @@ Each Phase 14 workbench lesson (31-42) ships a `mission.md` briefing the agent b

</details>

<a id="phase-19"></a>
<details id="phase-19">
<summary><b>Phase 19 — Capstone Projects</b> &nbsp;<code>17 projects</code>&nbsp; <em>2026 end-to-end shippable products, 20-40 hours each.</em></summary>
<br/>
Expand Down
6 changes: 4 additions & 2 deletions ROADMAP.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ Status tracker for every phase and lesson. The status glyphs in this file feed
the website (`site/build.js` parses them into `site/data.js`); do not change
their shape.

Total estimated time: ~314 hours, at your own pace.
Total estimated time: ~316 hours, at your own pace.
Comment thread
coderabbitai[bot] marked this conversation as resolved.
Outdated

**Legend:** ✅ Complete &nbsp;·&nbsp; 🚧 In Progress &nbsp;·&nbsp; ⬚ Planned

Expand Down Expand Up @@ -264,7 +264,7 @@ Total estimated time: ~314 hours, at your own pace.
| 21 | [Jamba — Hybrid SSM-Transformer](phases/10-llms-from-scratch/21-jamba-hybrid-ssm-transformer) | ✅ | ~60 min |
| 22 | [Async and Hogwild! Inference](phases/10-llms-from-scratch/22-async-hogwild-inference) | ✅ | ~60 min |

## Phase 11: LLM Engineering — ✅ (~17 hours)
## Phase 11: LLM Engineering — ✅ (~19 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
Expand All @@ -283,6 +283,8 @@ Total estimated time: ~314 hours, at your own pace.
| 13 | [Building a Production LLM Application](phases/11-llm-engineering/13-production-app) | ✅ | ~120 min |
| 14 | [Model Context Protocol (MCP)](phases/11-llm-engineering/14-model-context-protocol) | ✅ | ~75 min |
| 15 | [Prompt Caching & Context Caching](phases/11-llm-engineering/15-prompt-caching) | ✅ | ~60 min |
| 16 | [LangGraph: State Machines for Agents](phases/11-llm-engineering/16-langgraph-state-machines) | ✅ | ~75 min |
| 17 | [Agent Framework Tradeoffs](phases/11-llm-engineering/17-agent-framework-tradeoffs) | ✅ | ~45 min |

## Phase 12: Multimodal AI — ✅ (~65 hours)

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ def run_niah_grid(lengths, depths, seed=0):
needle = "the magic word is pineapple"
expected = "pineapple"
capacity = 20000
print(f" {'depth\\len':<12} " + " ".join(f"{n:>6}" for n in lengths))
print(" {:<12} ".format("depth\\len") + " ".join(f"{n:>6}" for n in lengths))
for d in depths:
row = []
for n in lengths:
Expand Down
2 changes: 1 addition & 1 deletion site/data.js
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
// Auto-generated by build.js — do not edit manually.
// Last built: 2026-05-25T10:54:44.943Z
// Last built: 2026-05-25T15:15:10.990Z

const PHASES = [
{
Expand Down