Anthropic 在 IPO 招股书中称愿为安全放慢发展速度
这段话出现在上市文件里挺少见——公司直接承认会为了安全接受落后。对比 OpenAI 一路高歌猛进的节奏，Anthropic 把安全写进招股书更像是在给监管和投资者打预防针。关注模型发布节奏和安全策略的人都该看看原文。
Anthropic 在其 IPO 招股说明书（prospectus）中写入了一段不常见的表态：公司愿意"以比实际能力更慢的速度推进，以让系统更安全，即使这会带来竞争劣势"。把这类安全优先承诺写进上市文件，在 IPO 材料中相当少见。
这条推文的作者 kimmonismus 认为，Anthropic 之所以敢这样写，是因为内部预测显示模型开发将继续明显加速，公司已在为此提前布局。换言之，放慢速度是建立在内部对发展节奏的判断之上，而非单纯的风险声明。招股书中的这段表述也可视为向监管方与投资者提前管理预期：即便竞争对手跑得更快，Anthropic 仍会把安全评估放在发布决策之前。
Interestingly, Anthropic is willing to "advance more slowly than we could in order to make our systems safer, even if that puts us at a competitive disadvantage."
Crazy thing to say in an IPO prospect.
In any case, Anthropic likely has internal projections indicating that development will continue to accelerate significantly, and is therefore already taking measures.
This report is categorized under AITOP's "Industry" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Key entities and technical topics under continuous tracking include Anthropic, AI安全, IPO.
Source attribution: curated from kimmonismus (@kimmonismus).
