Cross-Hotel Source Acquisition Benchmark: Full Results
Updated 24-run ledger including bounded Firecrawl recovery, retained sources, hashes, failures, and final package status.
Updated 24-run ledger including bounded Firecrawl recovery, retained sources, hashes, failures, and final package status.
A 28-route benchmark starting with only a hotel name and full address: models planned searches, selected websites, and faced deterministic retrieval validation.
Every query plan, selected website, raw response, scoring receipt, and retrieval result from the controlled hotel source-discovery 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.
Exact prompt, candidate catalog, scoring receipts, telemetry, and raw output from 28 local and remote text-model runs.
Executed first-step source acquisition for the Skokie DoubleTree, with the exact frozen source package the next no-web extraction card would receive and full failure/recovery disclosure.
The exact first-wave local-model discovery cards for three hotel classes, including complete prompts, limits, dependencies, outputs, receipts, and stop conditions.
Warwick Denver Workflow Canary V2: A Tiny Evidence-to-Publication Test Editorial illustration: a small canary-yellow figure at the edge of a quiet pool, standing in for the bounded canary test this post describes. Original Oddbyte image. This draft is incomplete; model-generated; experimental; may contain errors; not travel advice; based on one official page. It is a…
A non-production comparison of three local models summarizing the same two Coronado Springs reviews, with telemetry and known-error analysis.
A fully local, zero-cloud Warwick Denver review published as an intentionally imperfect capability-test artifact after passing factual validation but failing its style gate.