@_Mantic_AI co-founders @tshevl and @itsmebenday recently joined Radical Talks to discuss what it takes to build an AI system that forecasts world events better than the best human forecasters.

Does Mantic believe @elonmusk? It seems so, Mantic predicts Starship will achieve ship-to-ship orbital refuelling by 2028. Mars here we come. Full forecast here: blog.mantic.com/p/manchester…

We're living through a two-sided revolution in the technology of prediction: 1. Prediction markets (@Polymarket, @Kalshi). 2. AI forecasters. How do these compare? We benchmarked @_Mantic_AI against 4,000+ Polymarkets. Results: 🔵 $100k volume is the crossover point where the AI loses its superiority over the market. 🔵 At >$1M volume, the optimal forecast still requires giving Mantic 14% weight. 🔵 Mantic is better calibrated. This is for geopolitics, economics, elections etc -- we exclude sports and crypto. Personal thoughts: 1. "At what market volume do you lose your Brier advantage over the market?" could be the new METR time horizons graph. 👀 2. AI wins on scale. We can apply the "$100k-volume-level accuracy" to a universe of millions of questions. 🚀

Ben & I started Mantic with the mission to solve forecasting. This summer, Mantic out-predicted all 676 humans in the preeminent forecasting tournament. We’ve raised $25M to scale. We’re serving the brave decision-makers who want to grapple with uncertainty. Join the mission.

We ran a $25,000 contest to uncover: where do the best AI forecasting systems disagree about the future? The contest attracted superforecasters and hedge fund quants, who spent months probing for wedge questions. What were the winning tactics?

Mantic now makes *conditional* forecasts! This is a capability @itsmebenday and I have been excited about for a long time. What's conditional forecasting? You're looking at a Mantic forecast — e.g. of the oil price — and you want to see how it would vary under different scenarios, e.g. the Strait of Hormuz reopening. This is one of our most asked-for features, and it's taken some research to get right. We're currently treating it as an explainability technique. We give some examples in today's Friday Forecasts post (link in reply).

Inkling is our first open model from @thinkymachines and is now available on Tinker! Check out these quotes from Tinker customers on their experience with Inkling: @_Mantic_AI: "Not only does Inkling outperform Kimi K2.6 on our forecasting evals, it does so with half the output tokens." @trajectorylabs: "We’ve been impressed by how sharp and efficient the model is. Its reasoning is concise, its tool calling is consistently strong, and it holds up well on complex, long-horizon agentic tasks. It feels like a meaningful unlock for what teams can build with open-source models designed for customization." @lightningrodai: "We came away impressed by the model’s underlying reasoning ability. It’s thoughtful, original, and refreshingly unsycophantic.”

My ICML 2026 invited talk. Towards superhuman forecasting.

5 forecasts, every Friday. Follow along on Substack: blog.mantic.com/p/friday-for…

We sent Mantic's Fed rate path forecasts to the FT who compared us against the market. Mantic matched the market's accuracy overall: - In the first half of 2025, markets priced cuts that didn't happen, while Mantic was considerably less dovish across the entire term structure. - This flipped in the second half of 2025 w/ the Sep-Dec cuts where the market scored better. These results were using our general-purpose forecasting engine, without dedicated work. @gabrielpfritsch is now working on some upgrades -- so I'm looking forward to beating the market!

It’s day 2 at ICML and I’ve already met loads of people interested in forecasting, RL and @_Mantic_AI. If that’s you and we haven’t met yet, hmu on here or on the ICML app. Would love to chat! blog.mantic.com/p/mantic-at-…

RSVP: luma.com/3sc37zpa

Humans + LLMs has been standard at the top level of forecasting for a while, virtually everyone uses them. Trusting them beyond search and simulations was another story. With @_Mantic_AI, I've experienced a step change that might be as big as the move from manual Google to LLMs

Monitoring the Iran war on Polymarket and Kalshi has been a big upgrade, but it still feels like drinking the future through a narrow straw. We flew top forecaster @DrTournesol to London to ask Mantic any question he wanted about Iran. This exercise is a peak into future, not just of the war but of forecasting itself. Yann was one of the top ranked forecasters and question-askers on Metaculus last year. The best forecasters love collaborating with each other, but Yann has never had such a responsive forecasting partner as Mantic. This is like a "Claude Code moment" for understanding the future. Here are Yann's 28 key questions, most of which aren't on the prediction markets (link in reply).