← Back

Constitutional AI

technique 1 mention from 1 sources

Anthropic's method for training AI systems to be helpful, harmless, and honest through constitutional principles and AI feedback.

ai anthropic safety training
1

sources

Mentioned by

Nathan Lambert

All mentions

Nathan Lambert mentioned ✓ High confidence
"That's the older term for it coined in Anthropic's Constitutional AI paper."
From: State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI | Lex Fridman Podcast #490 • ▶ 1:41:14 • Jan 2026

Attribution: Nathan references Constitutional AI as the source of an older terminology in AI training methods