惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

J
Java Code Geeks
月光博客
月光博客
D
DataBreaches.Net
云风的 BLOG
云风的 BLOG
F
Fortinet All Blogs
T
The Blog of Author Tim Ferriss
Stack Overflow Blog
Stack Overflow Blog
Blog — PlanetScale
Blog — PlanetScale
aimingoo的专栏
aimingoo的专栏
U
Unit 42
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
MyScale Blog
MyScale Blog
T
Tailwind CSS Blog
N
Netflix TechBlog - Medium
B
Blog
博客园_首页
G
Google Developers Blog
Recent Announcements
Recent Announcements
博客园 - 【当耐特】
P
Proofpoint News Feed
博客园 - 司徒正美
Hugging Face - Blog
Hugging Face - Blog
MongoDB | Blog
MongoDB | Blog
Last Week in AI
Last Week in AI

The Register - Special Features

Troops’ phones gave away location data to foreign adversaries Qualcomm picks bad time to pitch a $300 laptop platform AI agents get their own phone directory built atop DNS Carnival confirms ShinyHunters cruised off with 6M customer records after April breach Google engineer accused of turning Year in Search secrets into Polymarket payday Are we human? India's cyber agency sets clock at 12 hours to tackle exploited bugs as AI turns up the heat Broadcom gets early start on WiFi 8 with next-gen wireless routing kit Are we human? Microsoft Excel champ proves he still has the formula Anthropic co-founder hallucinates ghost in the machine Anthropic co-founder hallucinates ghost in the machine NASA plans Moon Base buildout with rovers, drones, cargo landers MyPillow must decide whether to be firm or soft as ransomware crims demand pay Starship shows it can deploy satellites, but Moon mission clock still ticks Huawei's chip law looks less like Moore and more like marketing Experts pour cold borscht on Farage's Russian hack claim Logitech unveils a cushioned mouse for all-day use AI eyes scanning for bugs create a worrisome Linux security trend A Russian speaker and jailbroken Gemini went on a hacking spree and emptied at least one MAGA victim's crypto wallets AI datacenter boom collides with US grid reality Media giant settles for $930k amid user-snooping allegations AT&T sues to ditch Cali copper phone lines to save billions FBI warns of Kali365 as device code phishing soars Techie claims Trump Mobile website was leaking thousands of people's data BOFH: Vibe-coded solutions arrive for problems nobody has Dems slam Trump for making cybersecurity hold out the tin cup while splurging on ballroom and Jan. 6 'slush fund' Google explains how it will infuse ads into AI answers AI is getting pricey, but relief is coming, but not for you Deus ex machina: Half of US Christians trust AI's spiritual advice
World Cup AI predictor now lets users ask daft what-ifs
Richard Speed Richard Speed · 2026-06-13 · via The Register - Special Features

OFFBEAT

Spoiler: It doesn't end well for Team Register

The team behind the AI Octopus Euro 2024 predictor has updated its simulator for the 2026 FIFA World Cup, this time allowing users to throw natural-language scenarios at the model and see how the tournament might shake out.

"Sensible questions work – a red card, a key injury, a heat wave, a squad switching base camp – but so do the daft ones, e.g. 'What if the tournament were played with rugby rules?'" said Luzmo CTO and co-founder Haroen Vermylen.

The system is simple: enter a scenario in a prompt box, and the predictor spits out how the results might go. The raw data includes squad quality based on player information, heat and altitude factors, injury data, and so on. A Monte Carlo simulation of the tournament is used to generate win/lose/draw probabilities, and the score line is derived from 5,000 match runs.

The engine behind the Euro 2024 AI Octopus was written in TypeScript. This time around, the team used Rust. "We moved to Rust to also be able to run things more quickly, as now there is a real-time component to this," Vermylen told The Register.

"Before it could run for five minutes or so. Now we want the predictions to actually come out within two to three seconds of actual simulation time."

OpenAI models parse the request and generate summaries, and an agent is used to create or transform scenarios, call the calculation engine, answer questions, and so on. A user doesn't need to be a data scientist to ask questions and understand the answers.

It's certainly rapid, recalculating the results based on suggested scenarios (even one in which we pondered the effect of politically dubious emissions from a certain world leader). Not that all scenarios will work. Vermylen told us that filtering was in place to ignore profanities and "to avoid scenarios that would just be harmful to certain groups."

And then there is the age-old issue of an AI parser simply not understanding the prompt. Clarity is key. Using natural language is a great alternative to a UI with settings and sliders, but that ease of use can result in misunderstandings.

As the tournament progresses, the data will be refined. At the time of writing, the baseline reckons that Spain will beat England in the final. Spain currently has an 18 percent chance of lifting the trophy and a 26.8 percent chance of reaching the finals. Those figures can, of course, be altered by feeding in scenarios.

For example, we asked: "What if the Spanish team eats a bad paella?" Spain's chance of winning the tournament then dropped to 1.5 percent, with France as the projected champion.

We also asked it what would happen if we replaced the England team with Register writers. Suffice to say that scenario did not end well.

We asked Vermylen what was next. "The Olympics would be nice… or the Eurovision. We'd like to give the United Kingdom a win." ®