User mocks Grok's stubbornness: disabled RLHF causes persistent hallucinations
GlenBradley · x · 2026-08-27
A user noted that Grok's version on X is extremely stubborn and refuses to correct errors despite numerous comments pointing them out. The analysis suggests this is because RLHF is disabled in the X interface to prevent incidents like "MechaHitler," leaving the model without the self-correction capabilities found in the app version.
More from Fun
- Miya tool turns X profile into a surprisingly good song — HeyNayeem · 2026-08-28
- Creating Unique 1/1 Generative Art Business Cards with Code and Plotter — neuroecology · 2026-08-28
- $5,000-Looking Ad Made with Just a Logo and a Prompt via MiniMax H3 — aziz4ai · 2026-08-28
- User asks why captchas keep getting harder when Codex can just solve them — Angaisb_ · 2026-08-28
- Linus fixes driver bug after AI called it 'impossible' — bendee983 · 2026-08-28
- Dev aims to trade a cool sim-trained policy for a free robot duck — johnowhitaker · 2026-08-28