什麼是 ChatGPT’s Goblin Problem？
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.
截圖
?
還沒有評論，來搶沙發吧！
X 上關於 ChatGPT’s Goblin Problem 的真實討論
去 X 發文