How RLHF makes AI models more human-friendly

Claude vs Codex

Chapter 1

The Specialized AI Tools

Chapter 2

Mastering Different AI Skills

Chapter 3

Safety Ethics and Training

YOUR GOAL

Master of Claude vs Codex

Ch 3 · Safety Ethics and Training

federico Claude AI Safety Ethics

Constitutional AI! Claude learns ethical rules, to stay true and kind!

federico Why Claude uses a digital constitution for safety

Safe

BETA

federico Evaluate Claude and Codex outputs to master AI safety decisions.

federico How RLHF makes AI models more human-friendly

federico The challenge of bias in the Codex model

federico The importance of honesty in AI responses