Case study · a live, falsifiable head-to-head

Same wildfire question. Two very different answers.

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.

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

>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 40+ model roster. Even here it out-reasoned a single reply; the deep method marshals far more for the highest-stakes calls.

	Google Gemini	3Dogs Nexus
The answer	One range: 120k–170k	A calibrated probability spread (45 / 30 / 17 / 8%) around a plan-for number
How it reasoned	A single model, one pass	9 analysts argued it; 2 changed their minds after being challenged
Evidence quality	Sources cited	Every claim tagged VERIFIED / INFERRED / ASSUMED
Disagreement	None shown	A 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 really	Yes — a time-stamped forecast that resolves Oct 1
Speed & effort	Seconds · ~1 call	4m 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?”