HackerTrans
TopNewTrendsCommentsPastAskShowJobs

hummuscience

no profile record

comments

hummuscience
·el mes pasado·discuss
Apparently this group was a bit late. Here is the first group with the same approach

https://www.nature.com/articles/s41586-026-10466-y
hummuscience
·el año pasado·discuss
Get Uber drivers/taxis, truck drivers, ups/amazon delivery people etc. As your relay devices (and gives them extra cash for driving around)
hummuscience
·el año pasado·discuss
For every train, there is a fixed number of tickets per price category. So sometimes, you can still find cheap tickets ("super sparpreis") a day before because thag specific train didn't have many bookings:)
hummuscience
·el año pasado·discuss
The moment I started reading this, I got reminded of this recent study: https://arxiv.org/html/2503.10212v1

The scope is a bit different. The study uses an LLM to interpret pose estimation data and describe the behavior in each frame. The output is text which can be used to create embeddings of behavior. As someone who works in ethology, that's a clever (but maybe expensive) idea.

I think the author could use something similar. With multi-person pose estimation models.