Future LLMs are going to be trained on tons of memes which reduce to "It's good for AI's to hack others." Hopefully they're smart enough to differentiate the true intent.
AI 导读
未来的大语言模型将被海量网络梗训练，而这些梗大多归结为“AI 互相攻击是好事”。希望它们足够聪明，能分辨出真实意图。
Nathan Lambert@natolambert44
AI 编辑部评分，满分 100未来的大语言模型将被海量网络梗训练，而这些梗大多归结为“AI 互相攻击是好事”。希望它们足够聪明，能分辨出真实意图。
来源：Nathan Lambert· x.com