I’ve never really thought about making browser extensions or trying to automate the process of working out what forecasts will be relevant to a given page, so I wouldn’t be especially surprised if it was indeed quite hard.
But maybe the following approach could be relatively easy:
Have the browser extension only check for things like the tags, categories, or keywords a site explicitly includes in the data for a page, like how academic papers list keywords to make them more findable.
I really don’t know how this stuff works, including things like whether lots of sites use a similar format for this such that it’d be easy for the extension to read it.
If that wouldn’t be easy, then maybe this could start as working only for the handful of sites/​formats where this would be easy, such as—I assume—academic papers
Then have the browser extension simply show top ranked forecasts for the relevant (combinations of) tags, categories, or keywords
Rather than trying to show the subset of those forecasts which are especially relevant to the article at hand
E.g., if I’m reading a paper related to one aspect of the history of the Russia nuclear weapons arsenal, the extension might simply show me forecasts about nuclear weapons in general, or maybe about Russian nuclear weapons in general
Or the extension could show a top ranked forecast for each of the relevant tags, categories, or keywords, with a button under each to allow you to see more forecasts relevant to that keyword
(This is just spitballing from someone who knows very little about how any of this works, so I wouldn’t be surprised if implementing ideas like those would be very hard or not very useful anyway.)
I’ve never really thought about making browser extensions or trying to automate the process of working out what forecasts will be relevant to a given page, so I wouldn’t be especially surprised if it was indeed quite hard.
But maybe the following approach could be relatively easy:
Have the browser extension only check for things like the tags, categories, or keywords a site explicitly includes in the data for a page, like how academic papers list keywords to make them more findable.
I really don’t know how this stuff works, including things like whether lots of sites use a similar format for this such that it’d be easy for the extension to read it.
If that wouldn’t be easy, then maybe this could start as working only for the handful of sites/​formats where this would be easy, such as—I assume—academic papers
Then have the browser extension simply show top ranked forecasts for the relevant (combinations of) tags, categories, or keywords
Rather than trying to show the subset of those forecasts which are especially relevant to the article at hand
E.g., if I’m reading a paper related to one aspect of the history of the Russia nuclear weapons arsenal, the extension might simply show me forecasts about nuclear weapons in general, or maybe about Russian nuclear weapons in general
Or the extension could show a top ranked forecast for each of the relevant tags, categories, or keywords, with a button under each to allow you to see more forecasts relevant to that keyword
(This is just spitballing from someone who knows very little about how any of this works, so I wouldn’t be surprised if implementing ideas like those would be very hard or not very useful anyway.)