为什么一个 AI 比四个更好：Anthropic 多智能体实验与 LLM 同质化
🔮 Why one AI is better than four #598
Anthropic 用经典隐藏信息实验测试多智能体决策：四个智能体共享的证据指向错误选项，只有少数或单个智能体掌握正确线索，讨论后多数模型家族仅在 17-36% 的运行中选对，而把全部证据交给单个智能体时几乎每次都能答对，只有 Mythos 5 以约 85% 的表现部分例外。作者认为原因有二：LLM 缺乏多样性，30 个智能体做同一编码任务会有 18 个取相同的 git 分支名；智能体也缺乏让人类群体稳健的制度，如声誉、追责和对少数异议者的保护。文章还提到 State of AI 报告发现 token 弹性偏低，价格下降 10% 只带来 12-18% 的使用增长，并引用 Patrick Saner 的观点，认为真正重要的是完成一个有用工作单元的成本。
正文
当前显示原文，中文全文译文尚未就绪。
93 1 2 Share Good morning!
We are looking for an outstanding economist to join us as an AI Economy Research Fellow . If you know someone we should speak to, send them our way.
A few months ago, we (alongside Rohit Krishnan ) looked at whether AI is immune to groupthink . The answer was no. Blending several models’ answers kept about a quarter of the good ideas that had come from a single model. This is called the hidden-profile problem: when groups discuss what everyone already knows and don’t get to the knowledge that only one member holds. Anthropic has now run that classic experiment on agents: four agents must arrive at a decision. The evidence they hold in common points to the wrong option, while only a few agents (or just one) have the facts that lead to a correct decision. Getting it right means a small set of agents pressing its private facts and the others trusting them over the apparent consensus. After discussion, most model families chose correctly in only 17-36% of runs, while a single agent handed the entire evidence base got it right nearly every time. Only one model (somewhat) escaped: Mythos 5, at about 85% (why, we don’t know).
I see two problems at work here. First, LLMs lack diversity (they are low-variance): set 30 agents the same coding task and 18 of them will name their git branch identically. Second, agents lack the institutions that make human groups robust: reputation, recourse and protection for the lone dissenter. These aren’t necessarily unfixable, but it’s not yet clear what the fix is. On the diversity side, I particularly like the solutions Thinking Machines puts forward: an ecosystem of AIs raised in different places, with different values and purposes, “keeping the weirdness alive.” After all, most good ideas started weird.
In our State of AI report , we found a positive but underwhelming elasticity for tokens. A 10% price cut lifts token use by 12–18%: enough to raise total spend, but not by much.
Patrick Saner made a comment that made me rethink why: “the cost per token is irrelevant. What matters is the cost of completing a useful unit of work.” Elasticity might be underwhelming because users haven’t found a way to properly price “a useful unit of work.” Firms exist exactly to avoid pricing work. Especially for knowledge work, we buy a lot of it in bundles: a salary, a retainer, an hour. Creating a priceable task from knowledge work is not easy . Some may have found a useful unit : since October 2023 the top 1% of firms raised AI spend per employee by $6,542. The median rose only $9.63. I would guess this is mostly software, where AI is both most proven and, in a sense, most measurable (commits, pull requests and releases).