You could probably train something like that on semi-reasonable consumer hardware. Ads often have a very distinctive style and tone, and you need only a single output - the probability of it being any given second being an ad. It would probably take a lot to run though, you better hope the people who install the extension have good PCs. And, it would probably never get 100% accurate, you’d have to put up with still seeing some ads and having to rewind when it skips over valid video.
It’s usually even easier than that… In my jurisdiction, ads have to be clearly labeled and identified. It should be relatively trivial to detect this label.
And then Google sues the AI provider to stop them from doing that.
AI is not our tool, it is a corporate tool, for corporate profits, that they deign to let us dabble with, but only when it suits them.
There are plenty of open source ai, especially these single purpose one.
You could probably train something like that on semi-reasonable consumer hardware. Ads often have a very distinctive style and tone, and you need only a single output - the probability of it being any given second being an ad. It would probably take a lot to run though, you better hope the people who install the extension have good PCs. And, it would probably never get 100% accurate, you’d have to put up with still seeing some ads and having to rewind when it skips over valid video.
It’s usually even easier than that… In my jurisdiction, ads have to be clearly labeled and identified. It should be relatively trivial to detect this label.
it might even be ridiculously simple given that ads almost 100% of the time have louder audio than the content by design.