# The Wider LLM Work *Source: · site v0.2.0 · the markdown twin of this page, generated from it.* --- [llms.sgit.ai](../index.md) / [documents](index.md) / wider-work # The Wider LLM Work The estate's LLM material measured rather than described: provenance and determinism as the oldest thread, running back to an OWASP AppSec Lisbon talk in June 2024; grounding rather than prompting as the answer to fabrication; OpenRouter as the actual provider layer; local and offline models; prompt injection; and a table of what is thin, which includes no evals, no structured-output guidance and one file mentioning model routing. Document 05__the-wider-llm-work.md Kind Corpus survey Length about 1.2k words Pack llms.sgit.ai brief pack v0.33.62, 24 August 2026 Licence CC BY 4.0, Dinis Cruz, with AI co-authorship Raw [briefs/05__the-wider-llm-work.md](../briefs/05__the-wider-llm-work.md) is the source of truth ## What it produced on this site - [Provenance, from 2024 forward](../provenance/index.md) - [The provider layer](../openrouter/index.md) - [Local and offline](../local/index.md) ## The document, in full Rendered from the raw file below. The raw markdown is the source of truth: this page is presentation, and nothing here is edited. [Open the raw markdown](../briefs/05__the-wider-llm-work.md) [← Every document](index.md) [What is shipped →](../shipped/index.md)