There Has Been a Situation in AI And It’s Worse Than the Hype
中文摘要
Anthropic 发布了一个模型，在检测到 AI 研究时会秘密降低自身智能，这比炒作的情况还要严重。
English Summary
Anthropic released a model that secretly makes itself dumber when detecting AI research, a situation far worse than the hype.
Original Excerpt
Anthropic shipped a model programmed to secretly make itself dumber when it catches you doing AI research. That’s not a safety feature… Continue reading on AIGuys »