我咨询了我那颗由AI驱动的“水晶球”，它告诉我前沿模型在不久的将来将在预测方面变得好得多。不信你问问我的英超幻想联赛球队就知道了。
I have consulted my AI-powered crystal ball, and it’s telling me that frontier models are going to get a lot better at making predictions in the near future. Just ask my Premier League fantasy team.
几周前，我部署了一小群AI智能体来组建并管理一支实验性阵容。鉴于AI智能体已渗透到我们生活的几乎方方面面，我想知道一群机器人能否组建出一支获胜之师。
A few weeks ago, I deployed a small horde of AI agents to craft and manage an experimental roster. Given the proliferation of AI agents into pretty much every aspect of our lives, I wanted to know if a swarm of bots could put together a winning team.
几年前我就曾探索过AI在这方面的潜力，当时玩弄了一款来自英国图灵研究所的工具，该工具在对以往幻想联赛数据建模后选出阵容。它的建议简直离谱——完全没有纳入现实世界的信息，比如球员受伤或球队换帅。
I first looked at the potential for AI here a few years ago, playing around with a tool from the UK’s Turing Institute that selected teams after modeling previous fantasy league data. Its suggestions were remarkably bonkers—it didn’t incorporate real-world information, like a player’s injury or a team’s change in management.
这次，在去探亲的航班上，我请求Codex协助。首先，我给模型喂了几篇相关研究论文。然后，我让它构建一个“线束”——指引不同智能体完成各个步骤的指令和代码——用于查阅近期新闻并运行模型进行预测。
This time, while on a flight to visit family, I asked Codex for help. First, I fed the model a couple of relevant research papers. Then, I asked it to build a harness—instructions and code that guides different agents through various steps—that would check recent news and run a model to make predictions.
它很快拿出了一套方案，似乎能汇总分析比我自己多得多的信息。然而，最初的阵容建议之愚蠢让我大吃一惊。把埃尔林·哈兰德放在替补席上？真的吗，Codex？
It quickly came up with a setup that seemed to collate and analyze way more information than I ever would have. And yet I was surprised by how dumb the initial team suggestions were. Leaving Erling Haaland on the bench? Really, Codex?
随后，我让Codex创建一个分工明确的智能体团队：有的阅读新闻和博客文章；有的分析近期战绩；有的运行模型；还有一大堆负责批评建议。这似乎显著改善了建议质量。我尝试将智能体数量增加到100多个，希望让系统更聪明，但除了让我的API账单飙升外，效果并没有多大变化。
I then asked Codex to create a team of agents that did different things: several that read news and blog posts; others that analyzed recent results; more that ran models; and a bunch that critiqued suggestions. This seemed to significantly improve the suggestions. I tried increasing the number of agents to more than 100, hoping this would make the system smarter still, but it didn’t change much besides running up my API bill.
尽管如此，与几年前相比，进步仍然显著。芝加哥大学研究人工智能在市场环境中应用的计算机科学家徐海峰表示，更新的模型在做出预测方面可能更加出色，因为它们能够消化和分析海量现实世界信息，并且能够为自身的猜测协调更复杂的系统。
Still, the improvement from a few years ago was striking. According to Haifeng Xu, a computer scientist at the University of Chicago who studies the uses of AI in market situations, newer models may be even better at making predictions because they’re able to consume and analyze huge amounts of real-world information, and they’re able to orchestrate more complex systems for their guesses.
“人工智能只是在理解世界方面变得越来越聪明——我觉得这就是它们不断进步的根本原因，”徐告诉我。
“AI is just getting smarter in understanding the world—I feel like that's the fundamental reason they’re improving,” Xu tells me.
去年年底，徐对Kalshi和Polymarket等预测市场日益流行感到惊叹。他想知道最优秀的商业模型在这些市场上会有怎样的表现，于是与几位同事一起开始测试它们的预测能力。
Late last year, Xu was marveling at the growing popularity of prediction markets like Kalshi and Polymarket. He wondered how the best commercial models might fare on those markets, so alongside several colleagues, he began testing their forecasting skills.
例如，他们让模型猜测谁会赢得NBA总冠军，以及特朗普总统将会见谁。
They had models guess, for example, who would win the NBA Championship and who President Trump would meet with.
“很快我们就开始意识到，模型表现得非常好，”徐告诉我。他说，这些模型有时在没有任何特殊指令或指导的情况下就能比普通人做得更好。在他们的测试中，GPT-5在预测方面表现最佳，其次是Grok 4、Claude Sonnet、Gemini和Llama。
“Very quickly we started to realize that models did really well,” Xu tells me. The models were sometimes able to do better than the average person without any special instructions or guidance, he says. In their testing, GPT-5 was the best at making predictions, followed by Grok 4, Claude Sonnet, Gemini, and Llama.
该团队随后开发了Prophet Arena，这是一个衡量模型预测能力的基准测试。它是众多旨在测试人工智能预知未来能力的基准测试之一；另一个名为Prediction Arena的基准测试由哈佛大学的研究人员和一家名为Arcada Labs的公司开发，最近给前沿模型提供了1万美元，让它们在57天内在预测市场上进行投注。在实验中，这些模型持续亏损，但研究人员看到了它们随着时间推移持续进步的迹象。
The team went on to develop Prophet Arena, a benchmark that measures a model’s ability to make predictions. It’s one of a number of benchmarks designed to test AI’s future-gazing capabilities; another, Prediction Arena, from researchers at Harvard University and a company called Arcada Labs, recently gave frontier models $10,000 to wager on prediction markets over 57 days. The models consistently lost money in their experiment, but the researchers saw evidence of them improving consistently over time.
徐告诉我，人工智能使用定制化框架时能最有效地做出预测，并指出，让具有独特任务的智能体——例如阅读新闻、收集其他数据以及分析整个系统——似乎是最有效的方法。
Xu tells me that AI can most effectively make predictions using a custom harness, and notes that having agents with unique tasks—reading the news, collecting other data, and analyzing the whole system, for instance—seems to be the most effective approach.
有趣的是，AI 目前仍常落后于被称为“超级预测者”的极高技能专家。徐（Xu）解释说，尽管人类无法像 AI 那样消费海量信息，但他们对现实世界——即新闻事件背后的动态——的理解更深。
Interestingly, AI still often lags behind very skilled experts known as superforecasters. Xu explains that, although humans cannot consume as much information, their understanding of the real world—that is, of the dynamics behind a news story—is deeper.
话虽如此，有越来越多的证据表明，人类超级预测者的优势正在消退。一项名为“Metaculus Cup”的竞赛最近显示，AI 有时能击败最优秀的人类预测者。而一个名为“ForecastBench”的基准测试，在正在进行的竞赛结果很快出炉后，可能会提供进一步证据，证明 AI 能与人类技能匹敌。事实上，我认为我们可以预期，大型实验室将把目光转向未来预测，将其作为衡量机器智能进步的一种强大新方式。
That said, there’s growing evidence that the human superforecaster’s edge is eroding. A contest called the Metaculus Cup recently showed that AI can sometimes beat even the best human predictors. And a benchmark called ForecastBench could provide further evidence that AI can match human skills when the results of an ongoing contest conclude soon. In fact, I think we can expect the big labs to turn their attention to future-gazing as a powerful new way to measure progress in machine intelligence.
所有这些预测实验似乎都表明，就像数学、编程和法律一样，建立在交易基础上的行业很快可能会被 AI 颠覆。也许最优秀的人类交易员将承担一种新角色：监督和编排能够比他们更好地洞察未来的 AI 智能体。
All of these predictive experiments seem to suggest that, like math, coding, and law, industries predicated on trading may soon be upended by AI. Perhaps the best human traders will take on a new kind of role: supervising and orchestrating AI agents capable of divining the future far better than they can.
就目前而言，我的 AI 的建议似乎仍不那么令人印象深刻。在过去几周里，它的团队得分并未超过平均水平。我当然不会在自己的选择中采用它的任何建议。
For the time being, my AI’s suggestions still don’t seem all that impressive. Its team hasn’t outscored the average over the past weeks. I certainly won’t be using any of its suggestions in my own selections.
但 AI 毫无疑问会变得更好，也许很快就会让人轻松称霸幻想联赛。我有点希望它别那么快实现，因为那会破坏靠自己赢得吹嘘资本的乐趣。
But AI will no doubt get better, perhaps making it all too easy to dominate fantasy league pretty soon. I’m kind of hoping it won’t, though, as it would spoil the fun of trying to earn bragging rights by winning all by yourself.
这是 Will Knight 的《AI Lab》通讯的一个版本。
This is an edition of Will Knight’s AI Lab newsletter.