BitGarden

Recent Notes

  • 使用FalkorDB构建支持实时智能体的知识图谱,比Neo4j快496倍!

    Jan 23, 2026

    • cuts
  • 250122-skills

    Jan 22, 2026

    • ai/skills
  • 2026-01-22

    Jan 22, 2026

    • ai

See 575 more →

Home

❯

1 Inputs

❯

Article

❯

RLHF

RLHF

shareMar 31, 20231 min read

  • ai

资料

  • Illustrating Reinforcement Learning from Human Feedback (RLHF)
  • ChatGPT/InstructGPT详解 - 知乎

Graph View

Backlinks

  • 2023-03-31
  • ChatGPT 的训练原理科普

Created with Quartz v4.5.0 © 2026

  • GitHub
  • Discord Community