๐ด bad prompt: [error] fix.
๐ข good prompt: [error] reflect on 5-7 different possible sources of the problem, distill those down to 1-2 most likely sources, and then add logs to validate your assumptions before we move onto implementing the actual code fix.
@nichochar That's really amazing.
I couldn't believe it when the app asked me to log in to Google. I thought there was no way it could create a database right away.
๐ Robot localisation is the deca-billion-dollar problem no one talks about.
Every mobile robot needs to know its location to within 2-5 cm. Sounds simple? It's not.
Current solutions force an impossible choice: cheap but inflexible, or smart but fragile.
This fundamental trade-off is blocking the mass deployment of robots. Here's why - and how nature might solve it ๐งต
@levelsio This is incredible, I was wondering how you could improve the service and this feature is incredible. Does it generate 4k video with this? Is it probably very expensive?
@skalskip92 Do you have solutions for creating synthetic datasets? For example I need to track a certain bird species, but I don't have a dataset of images of these birds in the real world. Are there any solutions to create a dataset to train on synthetic artificially created images?