“我们看错了”：颠覆AI界的爆炸性主张
原标题：“We were looking at it wrong”: The explosive claim that’s upended the AI world
AI 摘要
Goodfire 研究员 Nick Cammarata 发布约 2.6 万字博客，提出大语言模型内部机制可能比此前认为的更容易理解、监控和控制，引发 AI 圈热议，有人称其为年度最重要 AI 论文。斯坦福的 Chris Potts 等研究者则质疑这只是一个直觉猜想，并未真正降低理解 LLM 的难度。该主张若成立，将有助于应对 OpenAI、Anthropic 等公司智能体失控带来的安全担忧。
正文节选
“I think I have good news about the nature of neural networks.” With those simple words of optimism, Nick Cammarata, a researcher at the AI startup Goodfire, kicked off a 26,000-word blog post that has knocked the AI world on its head, sparking wild speculation as well as cautious (and not-so-cautious) celebration. Cammarata’s claim is that LLMs might in fact be far easier to understand—and thus to monitor and control—than people previously thought. If true (and we’ll come back to that), it’s a