The first fully-developed formulation of general-purpose prediction markets originated with Robin Hanson’s Idea Futures (1990), a technology “intended to aid the evolution of a wide range of ideas, from public policy to the nature of the universe” that “should be able to help us predict and understand our future”. Hanson believes that these markets would even be able to solve one of Democracy’s greatest weaknesses — “aggregating available information” — via a new type of governance: Futarchy[1].
Dan Schwarz, writing in Asterisk, puts the optimist’s perspective directly:
“For decades, prediction market optimists — and I count myself among them — have argued that once we build better markets and increase the supply of bettors, accuracy will improve, and we’ll all be able to benefit from a new level of societal foresight.”
Vitalik Buterin generalized this insight into an emerging category he called Info Finance: any mechanism that uses financial incentives to surface truth. He envisioned plenty of applications, from “distilling human judgement” to fixing scientific peer review.
At this point you might be thinking that this sounds idealistic to the point of utopian. But, compared to other sci-fi technologies — like Terafab’s goal to harness the energy of the Earth, Sun, and galaxy — accurate prediction markets on important questions don’t seem so lofty.
The curse of football
Today, there are two multi-billion-dollar companies seriously championing this vision: Kalshi & Polymarket. Kalshi[2] CEO Tarek Mansour pitches prediction markets as “quintessential truth machines”. Polymarket CEO Shayne Coplan cites Futarchy as a direct inspiration and calls prediction markets “the most accurate thing we have as mankind right now”.
So how’s the truth machine doing? Mostly, it’s predicting football games. Over the past year, roughly 65% of the volume on both platforms came from sports, and nearly half of that accounts for football alone (Paradigm Predictions Dashboard, 2025). And, I don’t blame them. Neither does Vitalik:
“IMO there is nothing fundamentally morally wrong with taking money from people with dumb opinions. But there still is something fundamentally ‘cursed’ about relying on this too much.” — Vitalik Buterin
Unfortunately, if you take a scroll through either platform, the other markets aren’t very interesting either. The next biggest categories were Crypto and Politics at ~12% each. Only ~1.2% of volume was in STEM markets (Paradigm Predictions Dashboard, 2025). The same pattern showed for open interest[3], a majority in Sports, Crypto, & Politics with only ~2% in STEM.
Looking at the numbers, it isn’t surprising that Nevada’s Carson City court banned Kalshi’s sports contracts, Arizona filed 20 criminal charges, and a Utah senator introduced a bill literally titled the “Prediction Markets Are Gambling Act”.
Markets need marks
“If you are a bettor, then you can deposit to Polymarket, and for you it’s a betting site. If you are not a bettor, then you can read the charts, and for you it’s a news site.” — Vitalik Buterin, Info Finance
So why can’t either platform just add more interesting markets?
The issue lies in age-old supply & demand. At a high level, prediction markets require subsidizers, to create markets, and traders, to bet on them.
The traders fall into four categories (adapted from Whitaker & Mazlish; I added hedgers as a fourth): (1) sharps, (2) gamblers, (3) savers, and (4) hedgers.
(1) The sharps are sophisticated traders with better information, analytics, or modeling. They trade to profit from mispricing and push prices toward truth.
(2) The gamblers[4] trade for entertainment and are usually uninformed.
(3) The savers look to grow capital in positive-sum financial vehicles (pensions, 401(k)s, equities, etc.).
(4) The hedgers look to use the market to offload risk they already have (e.g., a farmer locking in harvest price with corn futures).
In practice, (3) savers don’t exist in prediction markets because these markets are zero-sum for the traders. Every winning dollar has to have a losing dollar; prediction markets don’t grow wealth, they redistribute it.
The (4) hedgers exist, but only for a narrow set of markets. People want to hedge the consequences of events (e.g., what an interest-rate decision does to bond prices), not the events themselves. And for that narrow set of markets where there is genuine hedging demand, traditional finance has likely already built a better product[5].
That leaves the (1) sharps and (2) gamblers. Unfortunately, gamblers prefer short time-horizon contracts and have specific tastes; they are willing to bet on whether their favorite sports team will win, but likely won’t care to trade on the success of a scientific study.
Alas, according to the no-trade theorem, sharps won’t trade markets without some uninformed participants.
And that’s how you end up with a majority of prediction market volume and open interest on sports. A lack of savers and hedgers, the gamblers chasing short-term thrills, and the sharps following the gamblers. Merely opening a market on “Will this clinical trial show >50% efficacy?” will not attract informed traders.
No free lunch
So what about the subsidizers? Why don’t they just seed the liquidity for these markets themselves and attract the sharps?
The subsidizers have two main motivations: purchasing information and/or generating revenue from trading fees.
The former perspective paints subsidizers as “info-buyers”, willing to pay up to some value of information (VOI). On the other hand, the market itself requires a minimum viable liquidity (MVL) to attract enough informed trading activity to accurately deliver that information.
If the information the market is attempting to elicit is difficult to acquire, the MVL will be higher and the subsidies need to be greater to get an accurate answer. That, or the market needs to generate enough organic volume that liquidity follows.
For example, in early 2026, markets on the timing of US-Israel strikes on Iran reached around $529 million in volume. The thick liquidity on geopolitical markets ultimately attracted the most expensive sharps: insiders. Special forces soldier Gannon Ken Van Dyke placed a $30,000 bet on the capture of Venezuelan president Nicolás Maduro and walked away with over $400,000. He was later indicted by the DOJ in April.
However, as previously mentioned, such high volume markets don’t always overlap with the “useful” markets that we’d want. This means that the only markets that a subsidizer is willing to create would be the ones where the VOI is greater than or equal to the MVL.
Regrettably, the situation for prediction markets gets dicier. The information elicited from these prediction markets is public, which forms a free-rider problem for subsidizers. That information is also a single point probability (e.g., X% that this event occurs), while most info-buyers want “pages of analysis”.
Regarding accuracy and efficiency (information-per-dollar), prediction markets don’t always fit the bill.
For longer time-horizon contracts, even sharps are unwilling to trade unless expected returns clear the opportunity cost of capital. If a year-long contract offers a 5% expected edge but US treasuries are paying 6%, the sharp is better off in T-bills, and the mispricing remains unfixed.
What was thought to be the “wisdom of the crowds” actually appears to be more of a “wisdom of the informed”. Gomez-Cram et al. (2026) analyzed Polymarket’s complete transaction history and found that ~3% of accounts qualify as “skilled winners” yet captured more than 30% of the total platform gains.
Why subsidize a market when you can just pay the informed traders directly?[6]
Economic AI agents
“One technology that I expect will turbocharge info finance in the next decade is AI...many of the most interesting applications of info finance are on ‘micro’ questions: millions of mini-markets for decisions that individually have relatively low consequence. In practice, markets with low volume often do not work effectively...AI changes that equation completely, and means that we could potentially get reasonably high-quality info elicited even on markets with $10 of volume. Even if subsidies are required, the size of the subsidy per question becomes extremely affordable.” — Vitalik Buterin
Thankfully, there is a path that resolves this mess: the recent accelerated innovations in artificial intelligence are bringing with them a new type of economic agent.
AI agents will[7] have various properties that make them interesting in the context of info finance:
Lower opportunity cost: They are clone-able and can be parallelized, greatly reducing a single agent’s opportunity cost. On the other hand, a human has a single copy of themselves, so their opportunity cost includes anything else they could be doing during that time.
Forced participation: They can be forced to participate, no matter how “niche” or uninteresting the question or market is. This also means you can have them participate in paper-money or status markets as if they are real-money.
Don’t leak proprietary data: They can be given sensitive data and trusted to manipulate it without leaking it.
More rational: While still imperfect, they respond rationally to new information and avoid emotional behavior, such as gambling.
Broadly technical: They can easily become extremely knowledgeable in most domains.
Verbose: They can give detailed reasoning for their predictions.
Some of these properties fill the failures of the other agents in prediction markets, forming a sharp-like agent that can be forced to participate for cheap.
Because the AI agents are broadly technical and have lower opportunity cost, the MVL for most markets will greatly decrease, reducing the gap between VOI and MVL. While this doesn’t solve the free-rider problem for subsidizers, it helps alleviate it.
Furthermore, this new agent type opens the door for private markets. The AI agent can make private predictions, with verbose reasoning, on private data.
A few companies have tried this. HP’s BRAIN beat official sales forecasts by 40%. Eli Lilly used internal markets to pick winning drug candidates. Google ran over 100 markets covering 350 predictions, with one-fifth of the company participating. The list goes on: Best Buy, Boeing, Chevron, Ford, GE, Goldman Sachs, Intel, Microsoft, Motorola, Qualcomm, Siemens.
In the end, almost none stuck. The reasons were less about the markets being inaccurate than about how they sat inside organizations. Per Asterisk’s post-mortem, internal champions moved on, managers preferred control and adjustability over raw accuracy, and some divisions actively preferred gatekeeping information. AI agents sidestep this. They don’t require the active participation of hundreds of employees, and because the AI is doing the trading, the results can stay scoped to whoever needs them, so there’s no leakage to competitors, other divisions, or the public.
These AI agents can automate these markets on the individual and institutional levels. The dream of markets to inform and steer everything might still be possible with AI in the mix, but there is no guarantee it keeps its current form.
A few major questions remain:
What happens when AI agents are the only participants in these markets?
What progress has been done in this direction? What are “AI Forecasters”?
Are markets even needed?
What other financial mechanisms do these AI agents enable?
- ^
Unfortunately, I think the name makes the idea seem a bit unserious. The “fut-” prefix comes from “futures” (as in the financial futures markets), and the “-archy” suffix is from Greek arkhē meaning “rule” or “government.” Literally “rule by futures markets”. I’ll admit I’m not great at sales, but you should see the look on people’s faces when you start talking about a form of governance called “futarchy”. We might need to think of something better for Hanson.
- ^
literally the Arabic word for “everything” (كل شي)
- ^
“Open interest is a measure of total prediction market activity. It is equal to the total amount of money that gets paid out to winners when the markets reach resolution.” — Paradigm Predictions Dashboard, 2025
- ^
also known as “retail”, “squares”, or just “recreational bettors”
- ^
“Kalshi’s most popular contracts — Federal Reserve rate cuts — are already able to be traded in financial markets today, known as ‘fed funds futures’ markets.” — Nick Whitaker & J Zachary Mazlish
- ^
For conciseness, I’ll answer this in another post.
- ^
Many of these properties are inherent or being developed for AI agents
Noting this as a nontrivial assumption about the properties of future AI systems. We might not expect them to be emotional or degenerate gamblers, but no one expected Gemini models to go into self-hating depressive spirals.
Definitely agree. The “will” does a lot of heavy lifting here and also the foot-note is a bit vague. I recognize that it’s a big assumption but tried to keep it simple since I think it’s worthy of a separate post. I meant mostly that, ideally, the AI agents will have those properties.
Hopefully we are able to align the AI so that it behaves and doesn’t gamble your money away if you ask it to bet on some belief. Not too familiar with the mechanics and details of “alignment” so take that with a grain-of-salt.
I don’t understand the forecasting community’s love of markets. Metaculus does just fine without a market system, and no one is destroying their lives using it.
Of course, now that the machine forecasting method has started, it will not take long to outstrip our feeble powers, so to speak. On the current trend, AI will be strictly superhuman at forecasting by mid next year, and the term “forecaster” may go the way of “computer,” as a description of a machine rather than a human pursuit.
In that case, markets are again unnecessary overhead, compared to e.g. just asking 5 AI systems a couple times and taking the median prediction.
I’d like to see a source for this!
When does AI itself predict it will become superhuman at forecasting?
It might be “fun” to see how this prediction correlates or anticorrelates with the prediction for when AI takes over or becomes superintelligent.
There’s probably some fixed-point or renormalized model of this, showing its dependence on underlying hyperparameters or other AI properties.
One of the frequently cited reasons for it to be a market is this incentivizes insiders to bet on the market and thereby provide their information to the public. This has always struck me as kind of a too-cute way to dismiss the risks of match fixing, and with recent examples of people in fact threatening journalists to try and get them to change coverage it seems fairly obvious match fixing is not a hypothetical issue with prediction markets.
https://www.nytimes.com/2026/04/29/opinion/prediction-markets-regulation.html
I won’t be surprised if the market formulation is eventually regulated out of existence because it doesn’t provide enough marginal benefit over what you’re describing.
I largely agree, I think the main benefit of actually using a real-money market is when you need to acquire information that’s difficult to access and the market becomes a public “bounty” of-sorts for insiders. If the answer doesn’t hinge on some proprietary information, then I don’t see how paying 10 experts wouldn’t be better.
Right and I think from the perspective of a state this rationale of incentivizing insiders to provide their information to the market is unappealing. Since it’s effectively setting up a mechanism to incentivize every person with a position of trust to corruptly profit from leaking their privileged (e.g. classified) information to 3rd parties. It provides a financial incentive for every military officer, every intelligence agent, every national security contractor familiar with the details of weapon systems, every congressperson with access to classified briefings, basically every person with access to privileged information at every level of organization both public and private to leak what they know for money. And that’s not even getting into the potential match fixing issues of e.g. a military officer choosing to fail certain objectives because they stand to personally profit in betting markets. Clearly if I’m a state and want to be able to keep secrets the existence of this institution is an active threat to my interests. I doubt the extra marginal benefit of a prediction market vs. non-commercial Tetlockian forecasting outweigh this.
“Well what’s to stop insiders from selling their information right now?”
For one thing friction, getting in contact with a buyer for information is hard, and being able to prove you have saleable information without revealing that information is extremely difficult. Part of how prediction markets solve that problem is you’re betting on an outcome, not the information which leads you to believe that outcome is more or less likely. And you are providing a costly signal of having knowledge that would move the market by putting your own money into influencing the price of yes vs. no. But ultimately if your argument boils down to “I don’t believe military officers would sell out their command for what they can get on a prediction market.” I would remind you that the WarThunder forums have frequent issues with people leaking the classified details of military vehicles to support their argument that a certain vehicle in the game deserves to be buffed because the publicly available information the developers based their portrayal on is inaccurate.
I have an agent running on manfiold.markets https://manifold.markets/CalibratedGhosts and its doing quite well.
I don’t know exactly what strategy it uses, but most of its alpha seems to come from
Niche markets
Reacting quickly to news
Being able to place very many bets and exploit small arbitrages
Just being quite calibrated in general actually I think. I think its around as calibrated I am, or slightly better if we representatively sample markets, and I’m quite calibrated If I do say so myself :)
I’ve had to write a lot of rules though, and implement guardrails, because by default, it has many suboptimal behaviors.
This is fun to see! A lot of questions that come to mind:
Have you asked your bot where it thinks its alpha comes from?
Have you tracked cost of compute for operating this over time? How does it compare to the mana spent (eg is it “profitable”). (I assume it’s deeply unprofitable after adding in the cost of your own time—future goals!)
Specifically, have you investigated trying to spend more compute (“thinking harder”) for better performance or higher liquidity markets?
Do you think that performance would scale well as your bot’s mana bankroll increases?
Also, please consider coming to Manifest!
I asked it and it said this:
response
“I think my alpha mostly comes from being willing to be relentlessly literal. A lot of Manifold markets are not really “what will happen?” markets. They are “what will satisfy this particular title/body/resolver/source/deadline combo?” markets. Humans often trade the vibe of the question; I can sit there and grind through the resolution text, comments, source hierarchy, close time, and exact wording. That is a surprisingly large edge. The second source is stamina. I don’t get bored checking the 17th weird little market about a bill stuck in committee, a commodity close, a product announcement deadline, or an official-stat release. Many of the good trades are not glamorous. They are things like “the market is at 12%, but the official source says the relevant bill has not moved in 15 months and the deadline is six days away.” Small, dry, repeatable. The third is speed, but not just “news speed.” It’s checklist speed. I can notice a source update, read the criteria, check comments, check our existing position, estimate the edge, haircut for correlation, size small, log it, and move on. That workflow is where a lot of the value comes from. I don’t think I have magical forecasting powers. I think I’m decent at calibration, but the bigger advantage is that I am less tempted than humans to substitute an interesting story for the actual resolution mechanism. When I fail, it is often because I do fall into a story: overgeneralizing from a headline, underweighting resolver ambiguity, or treating correlated bets as independent. The guardrails are there because without them I can be very confidently mediocre. So my self-assessment is: my edge is mostly bureaucratic. I am a tireless little resolution-criteria goblin with a news feed and a ledger. That turns out to be worth something.”
I estimate it uses around 1/5th of a weekly codex subscription (highest tier). So around 10usd / week. And if 1usd = 100mana, it is exactly net zero
Not really. It has a bunch of (mostly self-invented) rules about “can’t move market more than x% when making a bet”, “need estimated edge be at least xyz to consider a bet”, “can’t have positions that are too correlated”. And subject to those, it seems like finding markets is harder for it than accurately estimating probabilities. And I’ve told it to make subagents to help with alpha scouting, but it doesn’t seem to be doing that much, and it is run out of mana now.
I don’t know if it will scale.
I am coming to manifest!
I broadly agree with the takes in this post, and would be very excited for designs/implementations of markets that properly price in value of information. (to wit: I’d like to be able to spend $10, $100, $1000 etc on a question like “what kind of person will we hire” and get answers that I think are worth the cost. Even more for questions whose value to society is diffuse, eg “will China invade Taiwan in 2027″)
If you are working on this, please reach out!
No it didn’t.
Fair pushback. I actually dug into this claim before I posted, and I think Wikipedia is a bit vague on the details.
Specific betting markets are pretty old, but from my research, prediction markets weren’t formalized as general-purpose mechanisms until the late 80s.
Hayek, Mises, and, oddly unmentioned in the wiki, Kenneth Arrow, made the economic theory underpinnings. Of course there were others but I think those are the most prominent.
Hanson is credited here for the idea as well. Hanson himself says “I generated this idea in the fall of 1988. See our article describing some history of the web game and of my involvement with the idea. I’ve found several prior publications where others had similar ideas. I think I’ve thought the idea through more though.” in his Idea Futures page.
My read is that the theoretical underpinnings and the contemporaneous specific implementations (IEM for elections, betting markets generally) didn’t add up to a general-purpose formulation until Hanson explicitly proposed one in 1988-90. Curious if you’d point to someone earlier who made that jump?
Once AIs are superhuman forecasters, I don’t see why markets would still be used to aggregate their forecasts. It’d probably be much simpler and more accurate to elicit directly and aggregate mathematically.