Bro ai via programming with people is already good enough to fight wars with drones in the air. You don’t even need LLMs or machine learning black boxes.
Basically the reason is because there’s so little noise in the air. If it’s black and metal and flying and doesn’t match the iff signal than simple “if then” logic can verify it’s a bogey.
This is partly true, Automated object detection already exists. If LLMs haven't fundamentally shifted Ukraine war yet then it's plausible it has limited value in progressing drone warfare.
I disagree you can simply automate it via IFF though... basically because IFF is easy grounds for counter drone attacks. Establishing IFF just makes your enemies job easier unless you have heavy anti drone tech which no country does yet.
Automating "this person holding a gun in a given GPS grid is hopefully not holding a stick and is hopefully not a friendly/civilian... and calculate odds they should be executed" is not something easily done by a drone. Especially when there's electronic warfare and drones don't have the luxury of spending lots of time looking.
In Ukraine for example people wear 50 different uniforms because they buy them on the internet or come from random countries. And they carry similar AK rifles. What's an LLM going to do? Kill random people with ~50% accuracy using a very finite supply of drones? Or just have humans fly them from the rear.
Building 1000's of drones capable of taking out armoured vehicles from disposable commodity parts is more important than a 4% improved detection rate of hotdogs.
Basically the reason is because there’s so little noise in the air. If it’s black and metal and flying and doesn’t match the iff signal than simple “if then” logic can verify it’s a bogey.