RSSAmplifier

Home on Chris Hua · Dec 3, 2025

Kintsugi - AI mediation

0
Sign in to vote or save

This page cannot be shown here. You can still read it on the original site — the toolbar below keeps your place in the directory.

For a pile of sand, people really seem to think LLM’s are good at understanding human emotion and psychology. I certainly agree that they’re helpful. But as an AI researcher, I know that RLHF training pushes them towards responses that people like - not necessarily what they need to hear. Sycophancy is problematic in many areas, but especially when trying to resolve conflicts: if both parties talk…

For a pile of sand, people really seem to think LLM’s are good at understanding human emotion and psychology. I certainly agree that they’re helpful. But as an AI researcher, I know that RLHF training pushes them towards responses that people like - not necessarily what they need to hear. Sycophancy is problematic in many areas, but especially when trying to resolve conflicts: if both parties talk to a sycophantic LLM, they will get more entrenched in their views.

Read on /post/2025/12/03/kintsugi/

Comments

Nothing yet. Say the first thing.

    Sign in to join the conversation.