@pft @Viss The circular tracks are not the MQ-9s (those particular green/yellow tracks are probably DHS King Air planes). The MQ-9s were the hexagonal tracks–shown in an earlier article, but not the post.

@williampietri 👁️ What project was it for? sfships?

@simon @ian In case anyone's reading this and hasn't used instructor before, here's a working example: https://gist.github.com/wiseman/71571f12e4961faab7425f32a6afe74e

@ian @simon These examples may be helpful: https://github.com/jxnl/instructor/tree/main/examples/vision

@ian @simon The first thing I would try (because it's easy) is feeding images to GPT-4 and getting structured data back with the instructor library. Give it examples. If it doesn't work well, maybe see if a two-stage approach works better: 1. Get a natural language description from an image; 2. Convert that to the structured form.

@ai6yr Octal and binary forms of A515F9 (N427DP) and A95035 (N7DP) don't have any obvious correlation either--sometimes you see a bit flip or get stuck.

@ai6yr ADS-B Exchange had a single ping for N7DP around 2200Z–but Mode S, not ADS-B, and it had no mlat position. Not sure if there's any relation to N427DP, other than presumably FR24's MLAT solution putting them nearby at the same time. This chart shows the RSSI reported by ADS-B Exchange for N7DP (red) and N427DP (green), but I don't think any conclusion can be made from it.

@notsoloud @AE4WX @w7voa That would be my default assumption–GPS jamming in that area isn't constant, but it's been common for the past few months, so I would start by assuming it's coincidence. There are people who have a better idea of the typical pattern of jamming who might be able to say if this was typical. But first, we need the flight data–Does anyone know the aircraft or when it was flying?