sgit newsroom v0.1.29 · snapshot 2026-09-24

Reading room · llms.sgit.ai

On this page

Reading room / llms.sgit.ai · raw text · live ↗

From llms.sgit.ai, the page as fetched on 2026-09-25 · open the live page ↗Everything on this sheet is the source site's own text; the newsroom's chrome is outside it.

The Wider LLM Work

Source: https://llms.sgit.ai/documents/wider-work.html↗ · site v0.2.0 · the markdown twin of this page, generated from it.


llms.sgit.ai↗ / documents↗ / 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↗ is the source of truth

What it produced on this site

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↗

← Every document↗ What is shipped →↗