Glossary · Phase 6 · Modern LLM engineering
System card
A report published with a model describing its safety testing: what was tried, what went wrong and what was done about it.
Try it now
The fixes differ: access controls for misuse, evals for mistakes, and alignment research for the last kind.
Learn it properly
Alignment and safety · Making capable models behave as intended. About 35 minutes.
Other terms from the same lesson
- alignment: Making AI systems reliably do what people intend, safely and honestly.
- Q-learning: A simple reinforcement-learning method that learns a table of how good each action is in each situation.
- red-teaming: Deliberately trying to make a model misbehave, before release, to find and fix the problems first.
- specification gaming: When a system scores well by exploiting a loophole in how its goal was written, instead of doing what was meant.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.