| ▲ | jryle70 18 hours ago | |
You lost me. > 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. That isn't in the future. Anyone can do that today, and with clever judgement and luck, can find some other sites today. Not in the future, although future will likely be easier. He didn't say wait until next year for Gemini Dysprosium. That'd be hype. | ||
| ▲ | defrost 18 hours ago | parent [-] | |
It's also the past - we as humans have been flying multi instrument platforms and crawling through traces for decades now. Australia's been criss crossed with mag, gravity, lidar, gamma spectrometer, et al. since the 1970s and human operators have scrubbed glitches, filtered data, and composed maps leading to mineral discoveries, impact crater finds, unexpected structures found, etc. Elsewhere, Angkor was scanned back in 2012 leading to revelations and new structures w/out the use of AI- https://www.siemreapbest.com/temples/blog/angkor-lidar-lost-... | ||