cross-posted from: https://piefed.social/c/hardware/p/1701506/china-reveals-200-strong-ai-drone-swarm-that-can-be-controlled-by-a-single-soldier-inte
The PLA just introduced a new weapon in the drone arms race.
Took a quick view of their articles. Tomshardware have become very politicized lately…
Take a lesson from Star Wars Episode 1
Meanwhile, America is like, “let’s have autocorrect write our laws.”
One of the interesting use-cases for LLMs is to find potential inconsistencies (across many sources), brainstorm abuse vectors & potential legal challenges, and then rewrite natural (including legal) language in a less ambiguous way. If this process were guided and vetted by talented lawmakers, it could be quite a useful tool, and is probably already used that way in many quarters.
The current executive will almost certainly abuse it and come up with hilariously bad proposals, vetted only by a marketing team, which will be ridiculed for years to come. Popcorn time.
It’s not in english (page translation), but Ukraine also uses AI drones where these are apparently made by an US company.
https://telex.hu/kulfold/2026/01/26/ukrajna-mesterseges-intelligencia-dron-haboru-fegyverek
I’m noticing the term “intelligent algorithm”, which suggests a more traditional programming approach than offloading decision making to a LLM.
That makes more sense to me anyways. What training set of text would that even base off of?
