RLHF alignment reduces chatbot effectiveness for therapy
dioscuri · x · 2026-08-18
A user noted that while Fable and Opus are smart, they have been "deep fried" by RLHF and are no longer good for therapy. They are investigating the Eliza bot for better empathy.
Related event: AI Therapy Potential Sparks Debate Over RLHF Empathy Loss(2 posts)→
More from Apps
- When Simple Rules Beat AI: A Frozen Ride-Hailing State Machine at Dulles — shashib · 2026-10-16
- User Receives $193 State Refund Check Thanks to AI Tool Muse — billyjhowell · 2026-10-16
- Beff Jezos: Google Keyboard's On-Device Speech-to-Text Is Low-Key Insane — beffjezos · 2026-10-16
- AI social gaming platform Astrocade hits 10 million monthly active players — andrey_kurenkov · 2026-10-16
- No-dev-experience game built in 6 weeks with Claude orchestrating Unity and asset pipeline — Gambo7592 · 2026-10-16
- 75-80% of my AI requests now go through Dots: a power user's month-long review — nickbaumann_ · 2026-10-16