Cool story but:

> They turned the lidar strips (about 1,200 km² of jungle) into images, and 48 agents went through them one by one like very patient archaeologists, looking for pyramids, platforms, and plazas while filtering out natural hills, sinkholes, and roads. There was no special model or classifier involved: the agents literally looked at the pictures, following a precise guide.

Would it be better to ask a single LLM to create a processing pipeline to inject raw LIDAR data, create a heightmap and use an image classifier to identify unnatural shapes that standout and create a ranking score with a higher value where multiple shapes appears close to each other. At least you get something reusable and probably multiple order of magnitude faster.

▲

tantalor a day ago | parent [-]

For all we know, that's exactly what the agent did.

	▲	rerdavies a day ago \| parent [-]
		And who knows, perhaps a final filter to select "unnatural shapes that look like pyramids, platforms and plazas". :-) It really doesn't seem hard to believe that any of this is outside the capabilities of current gen LLMs. Including generating a plan to run multiple agents concurrently.