Hotel Step 3 Automation: Local Qwen vs Budget Cloud
A controlled Hampton benchmark compares local Qwen 3.8 with Alibaba Qwen 3.8 Flash and DeepSeek V4 Pro for reusable, hash-validated Step 3 hotel scoring.
-
-
What the Hotel Extractor Actually Found: 527 Evidence Claims Across 10 Hotels
A complete evidence table from a ten-hotel local-first extraction experiment: what the system looked for, the supported claim, exact source wording, criterion gaps, and telemetry.
-
Local Hotel Source Selection: 28-Model Benchmark
A grid comparing every installed non-coding, non-vision text model on the bounded hotel source-selection task, plus paired local-versus-remote speed trials.
-
Hotel Review Workflow Smoke Test: First Local-Model Cards
The exact first-wave local-model discovery cards for three hotel classes, including complete prompts, limits, dependencies, outputs, receipts, and stop conditions.
-
Local-First Hotel Review Capability Experiment — Models, Failures, and Usage
Experimental capability test report — this documents a non-production model workflow, including failures and incomplete telemetry; linked reviews may contain errors.