Six rules for putting a model anywhere near an investigation: assume it will be confidently wrong, keep every claim traceable to a fetched artifact, and treat a page you collected as something that might be talking to your model.
Recent Posts
One stage out of 6, and a short list of jobs inside it. The test that sorts the narrowing work a model can take on from the verification and attribution work it can only draft — and why that draft is a lead, not a finding, until a person has checked it.
One small real problem, walked end to end: fetching, a stable ID, storage, notification, scheduling, and the failure mode that looks exactly like good news.
Not AI, not robots. Six stages that every collection system turns out to be a version of — and the 4 cases where the right answer is to do it by hand.
A Python CLI and Chrome extension that exports public Google Maps to KML, KMZ, and GeoJSON — preserving layers, placemarks, and marker icons.
A beginner-friendly guide to installing and using the PWTT plugin for QGIS — the same radar-based method behind Bellingcat's damage maps, now available for anyone to run at home.
How I added Docker-based deployment to Turnstone (adsb-history), making it easy to self-host a full ADS-B historical query system — with or without Firebase and with support for external Postgres databases.
Tools & Resources from #DEFCON29 Recon Village Talks
Investigation Trends, Challenges, Methodologies & Strategies development - Forecasting OSINT landscape changing