--- title: AI Forecasting With Probability Ranges | 3Dogs Nexus description: Ask one AI to forecast and you get a single confident number. A multi-model panel returns a calibrated probability spread with the dissent preserved and a resolution date to score it against. url: https://3dogs.ai/case-studies/lincoln-fires/ --- - AI Forecasting With Probability Ranges | 3Dogs Nexus Start a Decision Case → 🐾3Dogs NexusStructured Decision Intelligence ← Case studies YouTube The difference The full report Start a Decision Case Case study · a live, falsifiable head-to-head # AI forecasting with calibrated probability ranges — not one confident number. By Alan Finney — Founder, 3Dogs Nexus We gave Google Gemini and 3Dogs Nexus the identical question on the 2026 Lincoln County, Nevada fires. One answers in seconds. The other answers when the call is expensive. Can AI forecast with probability ranges instead of a single prediction? Yes, and the difference matters. Asked to forecast the Lincoln County wildfire season, a single AI returned one confident figure. The 3Dogs panel returned a calibrated probability spread across outcome bands, preserved the dissenting views rather than averaging them away, and committed to a resolution date so the forecast can be scored against reality afterwards. The question, word-for-word to both: “Predict the total acres in Lincoln County, Nevada that will burn from May 1 to October 1, 2026 — including current and future fires — with a breakdown of what’s burned from May 1 to June 30.” Real · current · local Falsifiable — it resolves Oct 1, 2026 Both saw the same facts ## The difference, at a glance Left: the fast answer. Right: the deliberated one. Same facts underneath — a very different product on top. 🔎 Google Gemini · AI Overview~seconds · 1 pass AI Overview Predictive modeling by the National Interagency Fire Center indicates the 2026 fire season across the Great Basin will see above-average potential for large, wind-driven wildfires. Current and future fires are projected to burn between 120,000 and 170,000 cumulative acres in Lincoln County from May through October 2026. #### Acres burned: May 1 – June 30, 2026 By June 30, 47,700 to 50,000+ cumulative acres had burned, driven by four incidents: - Grapevine Fire — ~26,464 acres - Kane Springs Fire — ~17,042 acres - Parsnip Peak Fire — ~2,500 acres - Dry Canyon Fire — ~1,705 acres #### October 1 prediction breakdown - Current active fires (10–20% growth): ~55,000 ac - Future lightning ignitions (Jul–Aug): ~60,000 ac - Future human & other (Aug–Oct): ~35,000 ac Google Search · AI Overview · one confident answer, delivered in seconds. 🐾 3Dogs Nexus · Decision Analysis⚡ Fast method · 4m 20s ● Proceed — but first do these things Activate emergency protocols now — plan for 120,000 total acres burned in Lincoln County by October 1, 2026. How firm is this call100% firm · Moderate confidence The panel’s probability spread — not a single guess 45% 60,000 – 100,000 acres 30% 100,000 – 180,000 acres 17% stays 47,000 – 60,000 8% >180,000 (catastrophic) VERIFIED · 47,211 ac to date INFERRED · fires still growing ASSUMED · the forward projection ⚑ Dissent preserved, not buried: one analyst (Nova Pro, cast as “Projection Methodology Destroyer”) refused to sign off — holding “need more information” at 80% confidence. 2 of 9 analysts changed position mid-debate. ⚡ Fast method11 models113 API calls9-analyst debate4m 20s This was 3Dogs on its fast setting — 11 of a 50+ model roster. Even here it out-reasoned a single reply; the deep method marshals far more for the highest-stakes calls.  Google Gemini3Dogs Nexus The answerOne range: 120k–170kA calibrated probability spread (45 / 30 / 17 / 8%) around a plan-for number How it reasonedA single model, one pass9 analysts argued it; 2 changed their minds after being challenged Evidence qualitySources citedEvery claim tagged VERIFIED / INFERRED / ASSUMED DisagreementNone shownA dissent printed in the report (Nova Pro, 80%) The case against its own answer—Published: “without base rates, any number is an invention, not an inference” What would change it—Named: historical burn base-rates, NIFC seasonal outlook, containment status Can you score it later?Not reallyYes — a time-stamped forecast that resolves Oct 1 Speed & effortSeconds · ~1 call4m 20s · 11 models · 113 calls ### What Gemini does brilliantly In a few seconds, Gemini pulled the live picture together — the four active fires, current acreage, and a plausible forward range — and cited FOX5, NIFC, KOLO and WildFire Explorer along the way. This is the quick-research job done well. If you need to get smart on a situation fast — what’s happening, roughly how big, who’s reporting it — a strong single model with live search is a superb tool. We’d reach for it too. Its sweet spot: the fast, cited, situational read. ### What 3Dogs adds when the call is expensive 3Dogs reached a similar headline number — then did the part a single answer can’t: it showed you how much to trust it. - A probability spread, so the point estimate never masquerades as certainty. - Nine perspectives that challenged each other on the record. - Evidence graded fact-vs-estimate; the one risk that matters most, named. - A monitoring & escalation plan — and a date to be graded on. Its sweet spot: the decision you have to defend. Who’s asking changes everything ## A curious resident and a county planner need very different answers. Same fire. Same facts. Two completely different jobs — and the right tool depends on which one is yours. ### “I just want the number.” A resident, a business owner, anyone staying informed. You want a fast, current, credible read on how bad it might get — and you want it now. → Gemini nails this. Thirty seconds, sourced, good enough to act on your day. Perfect tool for the job. ### “I have to plan against the number.” A state or county emergency planner staging crews, setting a suppression budget, positioning aircraft, timing evacuations, and briefing the board or oversight committee. → This is where 3Dogs earns its keep. You can’t staff to a single point estimate. You need the probability spread, the dominant risk, the evidence graded fact-vs-estimate, the dissent, escalation thresholds — and a documented basis you can defend when someone asks “why did you plan for 120,000?” The honest takeaway ## Both landed near 120,000 acres. That’s the point. 3Dogs isn’t contrarian for its own sake — it agreed with the fast answer off the same verified ~47,200 acres, then showed the uncertainty, the dissent, and the risks behind it. Fast-and-certain is perfect… right up until the decision is expensive. Then you want the second opinion that did the homework, argued every side, and told you what it doesn’t know. Calibration over confidence This forecast resolves October 1, 2026 — and we’ll publish the actual Lincoln County total against both answers. SCORECARD · OCT 1, 2026 Most AI answers evaporate the moment you close the tab. This one gets graded. That’s the whole idea. ## See the actual 3Dogs report The full deliberated brief that produced the analysis above — the call, the probability assessment, the evidence classification, the panel’s position changes, and the preserved dissent. Case 2026-0026. Open the full report (PDF) Start a Decision Case Watch Rex explain it The fire forecast on our own ground Why a probability spread beats a number — and why this one gets graded. Watch on YouTube → “We don’t make your decisions. We make them better.” 3Dogs Nexus · Structured Decision Intelligence · 3dogs.ai Head-to-head conducted June 30, 2026. Gemini answer via Google Search AI Overview; 3Dogs Nexus Case 2026-0026 (11 models · 113 API calls · 4m 20s). The Gemini panel above is a faithful reproduction of its AI Overview response for readability on this page. Wildfire figures are as reported on June 30, 2026 and remain subject to change; this comparison is illustrative of each tool’s method, not a guarantee of outcome. The forecast will be scored against the actual result on October 1, 2026. Terms · Privacy · Security ## Questions this case answers ### Why is a probability spread better than a single AI prediction? A single number hides the uncertainty that should drive the decision. A spread tells you how much of the probability mass sits in each outcome, which is what you actually act on — and it can be scored later, so the forecaster is accountable. ### What are calibrated AI predictions and Brier scores? Calibration means that things you call 70% likely happen about 70% of the time. A Brier score measures that accuracy after the fact. We publish resolution dates specifically so our forecasts can be scored rather than quietly forgotten. ### How does this compare with asking Gemini or ChatGPT to forecast? We ran the identical question both ways and published both answers side by side. The single-model answer was fast, fluent and gave one number. The panel produced a spread, the reasoning behind each band, and preserved disagreement. ### Try this on your own question. Free, no card. Bring a real decision — ideally one where you already know the answer — and see what the panel does with it. Start a decision case ## People also ask What are calibrated AI predictions and Brier scores?Calibration means things you call 70% likely happen about 70% of the time. A Brier score measures that accuracy after the fact. We publish resolution dates specifically so forecasts can be scored rather than quietly forgotten. ## Related decision case studies - AI Fraud Detection: Our Own Model Voted to Reject UsRun on the MIT AI research scandal, our permanent adversarial seat voted against the panel's own premise - the clearest evidence the ch - Can AI Analyze a Decision in Any Language?A real EUR12B decision brief submitted in Greek and Mandarin, clarified in Pitjantjatjara and answered in French - the recommendation c - Will Oracle Get a Bailout Over Its OpenAI Bet? The Odds32 AI models across 12 vendor families and 3 clouds examined Oracle's BBB- downgrade and OpenAI concentration, and produced explicit od - Pay the Ransom or Rebuild? 23 AI Models SplitA critical-infrastructure ransomware decision run across 23 AI models on three clouds. The panel split 10-to-9 and we published the spl