ML 802 — AI Safety & Alignment

Prompt injection, jailbreaks, red teaming, refusal training, RLHF alignment, eval frameworks — making AI systems that fail safely.

BACKLOG · WORK IN PROGRESS

This topic is being written.

The metadata and shape of this page are stable, but the body content isn't ready yet. We'll publish it once it meets the bar of teaching something new with worked examples and real tools.

No guides have been written for this chapter yet.

Back to chapters Track progress on GitHub