How we build, evaluate, and improve Zeever.ca. We publish our methodology, results, and what we learned along the way.
October 21, 2026
AI Data Centres Now Ship in Containers. Municipalities Should Change How They Evaluate Them.
NVIDIA’s DSX POD cuts deployment to as little as 14 days. More of the skilled work happens in the factory, and councils still score these projects like factories.
October 3, 2026
Can Propane Power Canada’s AI Data Centres?
The propane industry puts its best opportunity at about 5 MW or less, and delivery arithmetic explains why. A 100 MW site needs 15 tanker deliveries a day.
September 23, 2026
A Quarter of a Trillion Dollars, Paid For and Not Running
Five companies disclose $250.2 billion of data centre assets not yet in service. We pulled construction in progress, NVIDIA inventory and server useful lives from the filings to test a claim about the AI buildout, and found one number that supports it, one that measures the wrong balance sheet, and one that is false as usually stated.
September 19, 2026
The Smaller Card Won Again
We moved our embeddings off a US provider onto our own GPUs. The 8GB NVIDIA card beat the 20GB AMD one again, and the move surfaced a months-old bug.
September 8, 2026
Our Vector Index Had Never Been Used Once
For months every search read all 58,000 rows. The answers stayed correct, which is why nobody noticed, and it wrecked a vector database comparison.
September 8, 2026
My GPU Benchmark Was Measuring a Cold Model
We published a GPU comparison for local language models. One finding was wrong: the first request after a model loads under-reports prompt processing.
September 3, 2026
Canada Now Has Two Data Centre Rulebooks. Only One Can Say No.
Ontario proposed a screening playbook and Ottawa launched a national framework. One gates access to the grid. The other has no metric and no consequence.
August 31, 2026
My Toronto.ca Corpus Contained Other People’s Websites
Toronto.ca redirects some of its own pages to other organisations, and my crawler stored them anyway. Cleaning that up moved retrieval accuracy eight points.
August 30, 2026
I Benchmarked 17 Models. The Problem Was My Benchmark.
Seventeen models scored within nine points of each other. Then I checked the benchmark itself and watched retrieval accuracy fall from 89 percent to 56.
August 23, 2026
Toronto Is 315 MW: What CBRE’s Data Changed in Our Data-Centre Research
CBRE now reports Toronto and Montreal on the same basis as US markets. We checked our series against it, corrected six things, and learned definitions rule.
August 12, 2026
AI Isn’t the Next 2008. But Its Financial System Is Starting to Rhyme.
Data-centre securitization went from $4 billion in 2020 to roughly $61 billion today, and SEC staff have now said qualifying versions are not legally asset-backed securities. This is not subprime. The risk is opacity.
July 31, 2026
Turbopuffer vs pgvector: Equal Quality, and a Speed Claim We Got Wrong
We benchmarked Turbopuffer against our pgvector setup on 100 Toronto questions. Answer quality was a tie, and still is. The 20x speed advantage was not: our pgvector index had never been used, so the comparison measured an unindexed table.
July 28, 2026
Does Proprietary Beat Open? Testing Cohere Command on City RAG
We put Cohere's three Command models against our open Qwen2.5-7B baseline on 100 Toronto questions, scored by a neutral judge. The open model held its ground.
Series · 11 chapters · July 23, 2026
Canada's Data Centre Race
An 11-part series on the physical foundations of Canada's AI buildout: data centres, power, fibre, water, sovereignty, jobs, and capital. Every figure cited.
May 2, 2026
Mapping Canadian AI Compute: Why We Built the Zeever Compute Index
A verified inventory of 39 Canadian GPU providers, normalized on H100 USD/GPU·hr against a $7.50 ceiling, with a sovereignty taxonomy that makes the procurement trade-off legible.
April 23, 2026
The Shift to Agent-First AI: What Model Deprecations Tell Us
AI inference platforms are deprecating chat-first models and replacing them with agent-first MoE architectures. What this shift means for production AI.
April 17, 2026
Running Ollama on an Old Dell XPS With an NVIDIA 3070
We tested local inference with Ollama on a Dell XPS with an RTX 3070 against Fireworks, Together.ai, and OVHcloud. The old desktop held its own.
April 3, 2026
Switching Inference Providers: A 24-Hour Latency Test
We ran a 24-hour latency test across Fireworks, Together, and OVHcloud. Together.ai was 1.7x faster. Here is why we switched.
April 2, 2026
The Missing Layer: AI Inference in Canada
Canada has GPU hosting but no easy way to test and prototype open-source models. That gap is pushing Canadian companies toward US-hosted black boxes.
March 31, 2026
100 Questions Across Toronto.ca: Building a Comprehensive Benchmark
We expanded our evaluation from 12 building permit questions to 100 prompts across 16 categories covering all of Toronto.ca.
March 30, 2026
Scaling a RAG Pipeline from 174 Pages to 35,000 Documents
Our database hit 25GB, the server crashed from OOM, and the web admin went dark during crawls. Here is how we fixed all three.
March 28, 2026
How We Built an LLM-as-Judge to Replace Keyword Scoring
Keyword matching scored our best answer at 0.00. The LLM judge scored it 1.00. Here is how we built a semantic evaluation system.
March 28, 2026
Comparing 7 Open-Source Models for RAG on City Data
We tested 7 open-source LLMs on Toronto city services questions. The cheapest model won.
March 27, 2026
Fixing Vector Search: Probes, Chunking, and Classification
Three retrieval fixes that improved citation accuracy by 35% and fixed queries that returned zero results.
March 27, 2026
Vector RAG vs GraphRAG on Toronto City Data
We compared plain vector retrieval against graph-enhanced retrieval. Graph mode helped on some queries and hurt on others.
Methodology notes
- All evaluations use temperature=0 for deterministic output.
- The judge model (GPT-oss 120B via Fireworks.ai) is the same model used for answer generation. We acknowledge the potential for self-evaluation bias.
- The 100-prompt benchmark suite covers 16 categories across all sections of Toronto.ca.
- Groundedness scoring evaluates whether claims are supported by retrieved evidence. It does not verify that the evidence itself is current on Toronto.ca.
Code and data
The evaluation framework, benchmark prompts, scoring code, and model comparison scripts are available on request. Contact us at infozeever [dot] ca.