Hacker News Reader

People voting me down probably didn’t get my point. If a tool is inefficient people won’t use it. A way to detect COVID that would produce many false positive would mine the spread of its use. Also, if the demographic sample is not done properly in theory you could risk having people underrepresented getting the wrong end of the stick. Imagine what this would mean in countries like USA!

lockdown is literally the goal. this is an example of a way to target such a lockdown instead of a blanket quarantine. if you can reliably get false negatives, you can clear people to go out.

"false negatives" => "true negatives"

If you can reliably get true negatives, you can clear people to go out.

Can't they use the data from people they test to further improve the model?

I think so. This is a good start for sure