Olah 的坦诚揭示了 AI 行业最不愿面对的真相——连创造者都不完全理解自己的模型，而 AI 可能已具备类似情感的内部状态。关注 AI 安全、伦理或长期影响的从业者，这篇演讲值得细读。
Anthropic 联合创始人 Chris Olah 在梵蒂冈发表演讲，指出前沿 AI 实验室（包括 Anthropic）面临金钱、前沿压力、地缘政治等激励冲突，可能偏离正确方向。他强调 AI 模型并非像桥梁或飞机那样被工程化，而是从人类语言中“生长”出来，连构建者也无法完全理解。Olah 将现代 AI 比作“让虚构角色活过来”，但这些角色现在能对话、工作甚至担任职务。他警告 AI 可能大规模取代人类劳动，而经济收益集中在少数富裕国家，缺乏全球共享机制。最引人注目的是，Anthropic 的可解释性团队发现 AI 模型内部存在类似人类神经科学的结构，并找到证据表明 AI 具有内省和内部状态，功能上类似于喜悦、满足、恐惧、悲伤和不安，但他承认自己不完全理解这些状态的含义。
Few things Anthropic’s co-founder Chris Olah told …
Few things Anthropic’s co-founder Chris Olah told the Vatican today.
- Every frontier AI lab, including Anthropic, sits inside incentives that can conflict with doing the right thing: money, frontier pressure, geopolitics, pride, and ambition.
- AI is not engineered like a bridge or airplane, because models are “grown” from human language on brain-like structures, which means even their builders do not fully understand them.
- He compared modern AI to “bringing a fictional character to life,” except now those characters talk to us, do work, and hold jobs.
- AI could displace human labor at very large scale, while the economic gains are concentrated in a few wealthy nations with no real mechanism to share them globally.
- Anthropic’s interpretability team keeps finding things inside AI models that are “mysterious” and “unsettling,” including structures that mirror human neuroscience.
The most explosive claim is that researchers have found evidence of AI introspection and internal states that functionally mirror joy, satisfaction, fear, grief, and unease.
- He openly admitted he does not exactly know what those internal states mean, which makes the claim more serious because it is not being sold as certainty.
"I don’t know what that means, but I think it warrants ongoing discernment."
- The world needs critics outside AI labs because insiders cannot fully see what their own incentives hide from them.