Level 00 / 100 XP
WPM0
ACC100%
TIME0:00
COMBO0
You
· DEAD HEAT ·
Cypher
🏁P1P2
🎮
👾
0%0%
0 / 1170%
0
×1
Reinforcement learning from human feedback aligns a model to human preferences by training it on comparative ratings.
Left index finger + Shift
Start typing — auto-detected on first keystroke