\( \newcommand{\vect}[1]{\mathbf{#1}} \newcommand{\mat}[1]{\mathbf{#1}} \newcommand{\R}{\mathbb{R}} \newcommand{\E}{\mathbb{E}} \newcommand{\Prob}{\mathbb{P}} \newcommand{\T}{^{\top}} \newcommand{\norm}[1]{\lVert #1 \rVert} \newcommand{\abs}[1]{\lvert #1 \rvert} \newcommand{\ihat}{\mkern1mu\hat{\boldsymbol{\imath}}\mkern2mu} \newcommand{\jhat}{\mkern1mu\hat{\boldsymbol{\jmath}}\mkern2mu} \newcommand{\pd}[2]{\frac{\partial #1}{\partial #2}} \newcommand{\argmax}{\operatorname*{arg\,max}} \newcommand{\argmin}{\operatorname*{arg\,min}} \newcommand{\cdata}[1]{\class{c-data}{#1}} \newcommand{\cmodel}[1]{\class{c-model}{#1}} \newcommand{\ctruth}[1]{\class{c-truth}{#1}} \newcommand{\cgrad}[1]{\class{c-grad}{#1}} \newcommand{\closs}[1]{\class{c-loss}{#1}} \newcommand{\cparam}[1]{\class{c-param}{#1}} \newcommand{\csecond}[1]{\class{c-second}{#1}} \renewcommand{\,}{\mkern3mu} \)

R04 · AI Safety and Governance

A free, illustrated L3 to L4 course of 8 modules in the Responsible AI track. Modules include: A taxonomy of risks; Evaluations and red teaming; Alignment basics.

R04 L3 to L4 · Advanced to Expert 8 modules · about 32 lessons Planned · Ring 4

Part of the Responsible AI track. Ships in Ring 4 (Expert) of the roadmap.

Modules

1. A taxonomy of risks
2. Evaluations and red teaming
3. Alignment basics
4. Specification gaming and reward hacking
5. Oversight and control
6. Regulation and standards
7. Risk management frameworks
8. Organizational practice

Signature illustrations

The pictures a learner should still see in their head a year later:

Risk matrix, evaluation pipeline, layers of governance.

Status

This course is planned, not written yet. It ships with Ring 4 (Expert).

Every lesson will follow the same twelve-part blueprint with at least three purpose-made figures. Watch the repository to hear when modules ship, or help write and review it.