-
No. 16Nov 2026
- Language models
- Maintenance and reliability
- Knowledge retrieval and reporting
- Open and synthetic datasets
- Evaluation and benchmarks
Does searching a site’s own work orders help a local LLM as much as a glossary?
The same local LLM read No. 13's 300 held-out mining work orders with ten of the company's other work orders, found for each by an offline SAG-Wiki search, in place of a 50-line glossary. Meaning came through in 290 notes with the search, 273 with the glossary run the same day (22 against 5 kept by only one) and 283 in No. 13's glossary run.
-
No. 14Nov 2026
- Language models
- Knowledge retrieval and reporting
- Documents and drawings
- Security and data privacy
- On-premises and edge hardware
How does SAG2 find cited answers in a mine’s records, offline?
SAG2, run in SAG-Wiki with the search sealed from any network, searched six public mining records for eight plant and safety questions, and a model on the same workstation answered each from the passages returned, citing them. Six of the seven searches with target pages returned those pages; 38 of 41 statements that cite a passage were fully supported by it, counting the record title sent with each.
-
No. 13Nov 2026
- Language models
- Maintenance and reliability
- Reading drawings and documents
- Open and synthetic datasets
- Evaluation and benchmarks
Does a site glossary help a local LLM read maintenance work orders?
Each of three mining companies had a 50-line glossary built from 3,200 of its own notes. Across 300 held-out work orders containing shorthand, a local LLM kept the meaning of 283 with the company's glossary, against 228 without it, and neither version said work was done that the note did not report.
-
No. 12Nov 2026
- Language models
- Mass balance and reconciliation
- Assays and lab data
- Agents, tools and skills
- Tailings and water
Can a local AI assistant tell which size fraction carries the most copper?
Given a published tailings table and Python, two local models named the fraction carrying the most of the reported copper in all 20 attempts. None said that the 8.2 % of the sample missing from the table might hold copper too.
-
No. 11Nov 2026
- Language models
- Laboratory and assay
- Reading drawings and documents
- Assays and lab data
- Documents and drawings
Can a local model put the right assay into the right database field?
With each field's method, unit and statistic spelled out, a local model got 83 of 84 fields right in each of three passes over seven certificates, against 55 for rules written from one certificate; its one miss made a gold standard's standard deviation (SD) three times too tight.
-
No. 10Nov 2026
- Language models
- Mineralogy and geometallurgy
- Geology and resource
- Evaluation and benchmarks
- Reading drawings and documents
What does a local LLM know about minerals?
Two local models, 976 questions rebuilt from a published test, grading checked by hand. Flash Next named a geology term from its definition 6 times in 10, but recalled a mineral's basic properties only 4 times in 10.
-
No. 07Nov 2026
What hardware does a mineral-processing site need to self-host LLMs and expert models?
An A$43,568 machine with one 96 GB card, plus a 16 GB tools card, runs GLM-5.3-Flash at an estimated 56 tokens per second for one 128K-token conversation. For the large expert models, RAM and the software stack matter: on one computer, the right stack, with its default drafting, wrote three to five times faster.