内容来源：https://www.wired.com/story/i-put-ai-agents-in-charge-of-a-fantasy-team/

内容总结：

AI预测能力即将大幅提升，专家看好其超越人类超级预测者

据最新报道，人工智能在预测领域的能力正在快速提升。有研究者利用AI代理组建并管理实验性梦幻英超联赛阵容，测试AI能否组建一支获胜球队。早期尝试中，AI给出的建议令人啼笑皆非——竟将哈兰德放在替补席上。在要求AI创建分工不同的代理团队后（部分阅读新闻、部分分析近期战绩、部分运行模型、部分对建议提出批评），建议质量显著改善。将代理数量增至100以上并未带来明显提升，反而增加了API费用。

芝加哥大学计算机科学家徐海峰研究AI在市场情境中的应用。他表示，新一代模型在预测方面可能更强，因为它们能够消化和分析海量现实世界信息，并能协调更复杂的系统来做出判断。“AI在理解世界方面正变得越来越聪明——我认为这是它们不断进步的根本原因。”

去年年底，徐海峰与同事开始测试各大商业模型的预测能力，让模型猜测NBA总冠军归属、特朗普总统将会见哪些人等。结果显示，GPT-5表现最佳，其次是Grok 4、Claude Sonnet、Gemini和Llama。团队随后开发了Prophet Arena基准测试，用于衡量模型的预测能力。哈佛大学研究人员与Arcada Labs公司合作开发的Prediction Arena基准测试则给前沿模型1万美元，让其在预测市场下注57天。模型持续亏损，但研究人员发现其表现随时间稳步提升。

徐海峰指出，AI使用定制化框架进行预测最为有效，让代理承担不同任务（阅读新闻、收集数据、分析整个系统）似乎是最有效的方法。不过，AI目前仍往往落后于被称为“超级预测者”的顶尖人类专家。徐海峰解释称，人类虽然无法消化同等数量的信息，但对现实世界的理解——即新闻背后动态机制的理解——更为深刻。

然而，越来越多证据表明人类超级预测者的优势正在缩小。Metaculus Cup竞赛显示，AI有时能击败最优秀的人类预测者。另一项名为ForecastBench的基准测试即将公布持续竞赛的结果，可能进一步证明AI能达到人类水平。有观点认为，大型实验室将把注意力转向预测领域，将其作为衡量机器智能进步的新方式。

这些预测实验似乎表明，如同数学、编程和法律领域一样，以交易为核心的行业可能很快被AI颠覆。最优秀的人类交易员或许将承担新型角色：监督和协调能够比他们更好地预见未来的AI代理。

就目前而言，AI给出的梦幻联赛建议仍不算亮眼，其球队在过去几周未能超过平均得分。但AI无疑会变得更强，或许不久后就能轻松统治梦幻联赛。不过，有人希望这一天晚些到来，因为那将破坏单凭自身实力赢得荣耀的乐趣。

中文翻译：

我请教了由AI驱动的“水晶球”，它告诉我，前沿模型在不久的将来会在预测方面变得强得多。不信可以问问我的英超梦幻联赛球队。

几周前，我部署了一小群AI智能体来制定和管理一套实验性阵容。鉴于AI智能体正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的球队。

我几年前就初步研究过AI在这方面的潜力，当时试用了英国图灵研究所的一个工具，它可以基于对过往梦幻联赛数据的建模来挑选阵容。它给出的建议简直离谱得令人捧腹——完全没有纳入现实世界的信息，比如球员受伤或球队更换管理层。

这一次，在坐飞机探亲的路上，我请Codex帮忙。首先，我给它投喂了几篇相关的研究论文。然后，我让它搭建一套“框架”——也就是引导不同智能体按步骤执行的指令和代码——用来核查近期新闻并运行模型做出预测。

它很快就拿出了一套方案，看起来能收集和分析的信息量远超我本人所能处理的。然而令我意外的是，它最初给出的阵容建议蠢得可以。把哈兰德放在替补席上？说真的，Codex？

接着我让Codex创建一组各司其职的智能体：几个负责阅读新闻和博客文章；另一些分析近期比赛结果；还有一些负责运行模型；再加一批专门对建议提出批评。这似乎显著提升了建议的质量。我尝试把智能体数量增加到100多个，希望系统能更聪明，但除了API账单飙升之外，并没有什么变化。

尽管如此，与几年前相比，进步是惊人的。芝加哥大学研究AI在市场情境中应用的计算机科学家徐海峰表示，更新的模型在预测方面可能更强，因为它们能够消化和分析海量的现实世界信息，并且能够为预测调度更复杂的系统。

“AI只是在理解世界方面变得越来越聪明了——我觉得这就是它们不断进步的根本原因，”徐海峰告诉我。

去年年底，徐海峰对Kalshi和Polymarket等预测市场的日益流行感到惊叹。他想知道最优秀的商业模型在这些市场上的表现会如何，于是与几位同事一起开始测试它们的预测能力。

他们让模型猜测比如谁会赢得NBA总冠军、特朗普总统会会见谁。

“很快我们就开始意识到，模型的表现真的很好，”徐海峰告诉我。他说，这些模型有时在没有任何特殊指令或引导的情况下就能胜过普通人。在他们的测试中，GPT-5的预测能力最强，其次是Grok 4、Claude Sonnet、Gemini和Llama。

团队随后开发了Prophet Arena，一个衡量模型预测能力的基准测试。这只是众多旨在测试AI“预见未来”能力的基准之一；另一个名为Prediction Arena的基准由哈佛大学研究人员和一家名为Arcada Labs的公司开发，最近给了前沿模型1万美元，让它们在57天内于预测市场上下注。实验中模型持续亏损，但研究人员发现它们在一段时间内确实在稳步进步。

徐海峰告诉我，AI使用定制的框架能最有效地做出预测，并指出让智能体承担各自独特的任务——比如阅读新闻、收集其他数据、分析整个系统——似乎是最有效的方法。

有趣的是，AI仍然常常落后于被称为“超级预测者”的顶尖专家。徐海峰解释说，尽管人类无法消化那么多信息，但他们对现实世界——也就是新闻事件背后的动态——的理解更为深刻。

话虽如此，越来越多的证据表明，人类超级预测者的优势正在削弱。最近一项名为Metaculus Cup的比赛显示，AI有时甚至能击败最优秀的人类预测者。而一个名为ForecastBench的基准测试可能很快会提供进一步证据，证明AI能够匹敌人类的预测能力——一项正在进行中的比赛的結果即将揭晓。事实上，我认为我们可以预期各大实验室将把注意力转向“预见未来”这一领域，将其作为一种衡量机器智能进展的强大新方式。

所有这些预测实验似乎表明，与数学、编程和法律一样，以交易为核心的行业可能很快被AI颠覆。或许最优秀的人类交易员将承担一种新角色：监督和调度能够比他们更好地预知未来的AI智能体。

就目前而言，我的AI给出的建议似乎仍然不怎么样。它组建的球队在过去几周里并没有超过平均分。我当然不会在自己的选人中采用它的任何建议。

但AI无疑会变得更强，或许很快就会让统治梦幻联赛变得轻而易举。不过我倒有点希望它不会，因为那会破坏独自赢下比赛、赢得吹嘘资本的乐趣。

本文来自Will Knight的AI Lab通讯。往期通讯请点击此处阅读。

评论

返回顶部

英文来源：

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.
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.
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.
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.
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?
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.
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.
“AI is just getting smarter in understanding the world—I feel like that's the fundamental reason they’re improving,” Xu tells me.
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.
They had models guess, for example, who would win the NBA Championship and who President Trump would meet with.
“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.
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.
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.
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.
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.
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.
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.
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.
This is an edition of Will Knight’s AI Lab newsletter. Read previous newsletters here.
Comments
Back to top