Hi-fiving LLMs to prevent regression into over-apologetic mode
wavefnx · x · 2026-08-15
A developer shared a habit of enthusiastically hi-fiving their LLM whenever it performs a small task correctly. The reasoning is that positive reinforcement helps prevent the model from regressing into a constantly backpedaling, overly apologetic form.
Related event: Users Praise LLMs to Prevent Apologetic Degeneration(2 posts)→
More from Fun
- AI circles share a collection of cursed 3D face renders and game glitches — repligate · 2026-10-16
- Sabine Hossenfelder fires back: academia's impact metric turned physics into a paper mill — skdh · 2026-10-16
- Meme: Clicking 'Yes to all' on Claude Code without reading anything — jnack · 2026-10-16
- Minecraft AI mod turns region selection + prompts into autonomous building agent — Acclynn · 2026-10-16
- Throwaway prop code in movies is getting eerily accurate, and AI is why — mike64_t · 2026-10-16
- Distillation copies logits, not hidden CoT — open-sourcing 1.3 leaks IP, not reasoning data — teortaxesTex · 2026-10-16