We built minds we cannot fully inspect. Now what?
L8 · Safety, Alignment & Society
This chapter treats safety as engineering, not opinion. Made-up answers have causes you can measure, bias has tests you can run, and jailbreaks have patterns you can catalog. You will watch a score climb while the thing it stands for gets worse, price the trade between answering and staying quiet, hunt failures the way a red team does, and put honest error bars on what you find. It ends with the rules, the electricity bill, and the parts nobody can answer yet.
- What Alignment Means
- Doing Exactly What You Asked
- Searching Harder Makes It Worse
- The Model Learns Your Taste
- Confident and Wrong
- Answer or Stay Quiet
- Bias You Can Measure
- What the Model Remembers
- Why a Refusal Breaks
- Going Looking on Purpose
- An Evaluation You Can Trust
- Looking Inside
- Misuse, Accidents and Uplift
- The Rules, in Plain Words
- Electricity, Work and What Nobody Knows