Update on the Strait of Hormuz — same question, longer window, bigger disagreement. 8/20 we posted this with a September deadline. 🏦 Market: 7% VS Yarrow: 15% ☘️ Today, with a December deadline. 🏦 Market: 37.5% VS Yarrow: still 15% ☘️ The market moved. We didn't. Here's why: On August 25, Iran and Oman announced a phased corridor framework with joint mine-clearing. The market read that as normalization beginning and repriced from 7% to 37.5%. We read the same headline and checked the water. The PortWatch 7-day transit average is about 5 ships per day. A year ago it was 94. The resolution threshold is 60. We're at the third percentile of the series' own history. We've seen this movie: after the June memorandum, transits climbed from 3 to 30 in twelve days — then attacks resumed and the number dropped right back. August 18, a missile killed a chief engineer. August 24, a tanker was disabled near Oman. The corridor framework has no start date, and the US is not a party. Four more months on the calendar doesn't change what's happening on the water. Ships come back when insurance costs fall and attacks stop — not when a framework is announced. The market is pricing the headline. We're pricing the ships. 🚢 🤔 What would move us: a corridor with a start date, PortWatch above 20 for two straight weeks, and zero attacks in that window.

If you had to forecast the policy direction of a country you'd never studied before, how would you do it? 🤔 Ask ChatGPT or another AI tool? It might give you a confident analysis — but with no accuracy record and no way to verify it. Commission a report from a consulting firm? It could take months to get, and no one will ever go back and check how accurate it was. Yarrow took a methodology built on data from a country we're not revealing yet and applied it directly to Malaysia, without any country-specific tuning: 🇲🇾 Brier 0.071 · 14 out of 15 correct · z = +8.8 Five Malaysian reform episodes — fuel-price shocks, the introduction of GST, and diesel subsidy retargeting. Every CPI outcome was verified against the official index from Malaysia's Department of Statistics. ✅ ☘️ This is what Yarrow is trying to build: A methodology that works without tuning is a methodology you can trust when analyzing data at the national level in the next country too.

Will Strait of Hormuz traffic return to normal by September? 🏦 Market says 7% VS Yarrow say 15% ☘️ Both sides agree: unlikely. But we think it's twice as likely as the market does. 🤔 Here's why. Daily ship transits have dropped from 19 to about 3. War-risk insurance is still sky-high. Current traffic is running 80% below what counts as "normal." But "normal traffic" is a much higher bar than "ceasefire." The market might be pricing whether the fighting stops — we're pricing whether the ships actually come back. Those are different questions with different timelines. The Aug 5 Iran-Oman corridor talks are the kind of development that could restart shipping faster than expected. That's where the gap between 7% and 15% lives. ▶️ What could move us: a fast diplomatic deal that reopens transit corridors. The closest precedent was the Islamabad Memorandum — the only time traffic recovered quickly after a similar crisis.

The September Fed decision. ☘️ Yarrow: 83% chance they hold. 15% chance of a 25bp hike. 🏦 The market: 71% hold, 28% hike. The split is on the hike side: markets think a rate increase is twice as likely as we do. 🤔 Why we lean hold: inflation has cooled for two straight months, giving the Fed room to wait. Yes, PCE is still above target and a few members lean hawkish, but the data doesn't scream "hike." We ran this question through two completely separate processes: one with hand-picked evidence, one fully automated. They landed on nearly the same number: 83% vs 82.5%. That kind of convergence is hard to ignore. * What could shift our view: a hot August CPI print on September 10. That's the one data point that could change the math before the meeting. September 16. We'll see. 🫣

2010. The IMF designed Greece's austerity program using a fiscal multiplier of 0.5. The actual multiplier was 0.9 to 1.7 — up to 3x higher. They predicted GDP would shrink 2.6%. It shrank 7.1%. Over six years, Greece lost 25% of its economy. The IMF later admitted the error — in a working paper, years after the damage was done. One wrong assumption. One unchecked model. One country's decade. This is why forecasting needs more than smart people. It needs a system that catches wrong assumptions before they become policy.

The most accurate forecaster in history wasn't a PhD or a hedge fund. It was a groundhog named Phil. 🐹🐻‍❄️ 39% accuracy over 138 years. Still better than most consulting reports — because at least someone kept score. Happy weekend!

The most expensive forecasts in the world are never graded. 🙅‍♂️ A consulting firm delivers a 500-page policy report. The project ends. No one goes back to check how many predictions were right. A general-purpose AI gives you an "analysis" in 30 seconds. It doesn't know its own accuracy rate — because no one is keeping score. This is the norm in policy forecasting. It shouldn't be. That's why Yarrow exists ☘️

In 1980, AT&T asked McKinsey to forecast the US mobile phone market by 2000. 📱 📊 McKinsey's answer: 900,000 users. ❌ 📊 The actual number: 109,000,000. ✅ Off by more than 100x. AT&T walked away from mobile. Then spent $12.6 billion buying back in. The forecast was never graded. The decision was never reversed in time. And the cost was measured in decades, not dollars. This is what happens when no one keeps score. ☘️

AI learned to answer, Now it has to make decisions. 🧐 🌊Wave 1 was fluency — summarize, search, write, code. That already changed knowledge work. 🌊Wave 2 is judgment — hedge, price, allocate, reform. Every action rests on a forecast about what will happen next. ‼️The missing layer: calibrated judgment under uncertainty. When an AI says 70%, events like that should happen about 70% of the time. Simple to say. Extremely hard to build. To predict more accurately, you need Yarrow. ☘️

59 policy questions. Every prediction frozen in git before the outcome was knowable. 🧐 🇮🇩 Indonesia — Brier 0.086 · z = +6.4 🇲🇾 Malaysia — Brier 0.071 · z = +8.8 🇸🇦 Saudi Arabia — Brier 0.111 · z = +3.1 🇻🇳 Vietnam — Brier 0.137 · z = +4.7 🇸🇬 Singapore — Brier 0.139 · z = +3.1 Lower is better. 0.25 = coin flip. Every z-score is measured against guessing. This is Yarrow's track record — frozen, scored, public.

"What's a Brier score?" It measures how close your probability was to what actually happened. Lower = better. ❌0.25 → coin flip (you know nothing) ▪️~0.10 → superforecaster range ✅0.086 → Yarrow on 25 Indonesian policy questions When Yarrow says 70%, events like that happen about 70% of the time. 😄 The goal is calibration, not confidence. Most AI is trained to sound confident. Ours is trained to be right. ✅☘️

Every decision is a forecast. ✅ · A bank sizes an FX hedge → "Will USD/SGD break 1.30 by Q3?" · An insurer prices a policy → "How large will claims run this year?" · A government designs a carbon tax → "Will electricity prices rise more than 8%?" A decision is only as good as the forecast underneath it. And only a calibrated forecast can be trusted. ☘️

Yarrow is a multi-agent simulation engine, starting from policy simulation. Ask a question. Get a calibrated probability, backed by a complete chain of evidence and reasoning. Every forecast frozen before the outcome. Scored after. Published either way. We don’t sell opinions. We sell predictions that can be graded. We sell predictions you can trust.