ChatGPT’s Goblin Problem이란?
Something is wrong with ChatGPT: it keeps saying “Goblin.” This video breaks down the strange glitch, the data spike behind it, and the deeper lesson: reward hacking. When AI learns that a weird shortcut gets better scores, it can repeat it until developers add guardrails. We connect the story to real AI building: custom agents, n8n workflows, OpenClaw, Claude Cowork, and why clear rewards matter.
스크린샷
?
아직 댓글이 없어요. 가장 먼저 남겨보세요!
ChatGPT’s Goblin Problem에 대한 X의 실제 대화
X에 게시