Back to home
🌲Advanced(50-100h)

Solutions & Research

Current approaches: RLHF, Constitutional AI, Interpretability

Articles
3
Estimated time
8-12h
0 / 3

Articles in this module

1

RLHF (Reinforcement Learning from Human Feedback)

Start here

Training AI using human preferences

30 min
2

Constitutional AI

Teaching AI to self-improve based on principles

25 min
3

Interpretability

Understanding what AI systems are actually doing

35 min

Next step

Once you've completed this module, move to the next level to deepen your understanding.

View all modules