The AI Superforecasters Are Here - by Scott Alexander

Astral Codex Ten

SubscribeSign in

The AI Superforecasters Are Here<br>...

Scott Alexander<br>Jul 02, 2026

206

104<br>29

Share

The annual prediction market conference was earlier this month. This was the year prediction markets went from an obscure hobby to a multi-billion dollar industry; from semi-illegal to having the President’s son as an advisor. I can’t remember if anyone talked about any of that. It didn’t even register. All eyes were on the AI superforecasters.<br>I met an AI superforecaster startup founder who told me his AI had turned $35 into $2 million on Kalshi over seven months. I met another who said they were beating the stock market by 25% with a market-neutral portfolio - of course this could be luck, but they’d beaten Kalshi and Polymarket by similar margins.<br>In fact, I believe all of these people. The extending-lines-on-graphs community has long predicted that AIs would beat the best human forecasters sometime in 2026 - 2027. What did you expect the bots-finally-beat-humans-at-predicting-the-future moment to look like? Vibes? Papers? Essays? In retrospect, sure: it will look like AIs making crazy profits on prediction markets and beating the stock market by some comfortable amount.<br>But what happens next?<br>Using An AI Superforecaster

Before getting into details, what exactly are we talking about?<br>An AI superforecaster is an AI - usually a frontier model like ChatGPT or Claude - which has been modified to be good at forecasting. This usually means a “scaffold” - a program that handholds it through a long research process with various prompts, tools, advice about when to create subagents, etc. The overall experience is a lot like using any other AI, but slower and more expensive, because it’s doing more work.<br>This might make more sense with an example. FutureSearch - the company that claims to be beating the stock market - kindly offered to let me try their AI superforecaster and write about it here.<br>For a test question - some Silicon Valley philanthropists recently started a project to end respiratory infections like the common cold. I decided to ask about their chances of success. Since forecasters need very precise questions, I asked how likely it was that the rate of colds would be cut in half by 2040:

By two minutes in, the AI had deployed three subagents, read 16 websites, and (at the exact moment I took this screenshot) was “investigating the scalability of ASHRAE Standard 241 air cleaning technology for widespread residential adoption by 2040.”

After five minutes, it had its answer: the chance of US respiratory infections halving by 2040 was 7% :

It explained:<br>The agents’ reasoning centers on a tough conjunctive chain of requirements that all must succeed simultaneously:<br>1: The biology is brutal. 200+ cold-causing viruses, 150+ rhinovirus serotypes alone — 50 years of vaccine efforts have failed, and experts as recently as late 2025 didn’t expect a cold vaccine within 5 years. During COVID lockdowns with unprecedented behavioral changes, rhinovirus incidence dropped only modestly and rebounded immediately.<br>2: Intercept’s own timeline is tight. Their roadmap projects commercialization 5–7+ years out, leaving little room to clear Phase 3 trials, FDA approval, and achieve mass deployment by 2040 — all for under $500M (likely far too little for that scope).<br>3: Adoption is a wildcard. For a mild illness, compliance with regular nasal sprays or prophylactics is expected to be low. Air-cleaning infrastructure faces steep retrofit costs and a mixed evidence base (a 2025 RCT of germicidal UV found no significant reduction in infections).<br>4: Measurement may be impossible. The US lacks routine population-wide cold surveillance, and the 2020–2026 baseline is distorted by pandemic-era behavior — making a verified >50% reduction hard to demonstrate even if real progress occurs.<br>The initiative is genuinely novel and credible, but halving cold frequency in 14 years without transformative AI acceleration is an extraordinarily high bar.<br>You could follow up by forecasting a softer threshold (e.g., 25% reduction by 2035), or by ranking the specific Intercept technical approaches (nasal sprays vs. vaccines vs. air cleaning) by their likelihood of meaningful impact.

…and, in case I wanted to learn more, cited its 212 sources. The forecast had taken five minutes and cost me $8 in credits.<br>But is it true? Ideally we would wait until 2040 and see. For now, I started by comparing its answer to another superforecaster AI. Preseen is the company that claimed to 100,000x their seed money on Kalshi. Here’s their answer:

8.8% compared to FutureSearch’s 7%, not bad!<br>Are either of these true? I asked a human superforecaster to predict this question, to see if she got the same as the AI. She said that depending on an ambiguity in the wording, she would give it 5-10%. Again, not bad!<br>Man Vs. Machine

Of course, it would be even better to do the same experiment...