| ▲ | amelius 2 hours ago |
| Maybe a better approach is to convert the page to an image, run OCR over it, use an LLM to remove the ads, present the result to the user. |
|
| ▲ | ImJamal 2 hours ago | parent [-] |
| How would you comment or watch a video if you did that? |
| |
| ▲ | amelius an hour ago | parent [-] | | You can still do that. The only thing I'm proposing is to do the filtering on graphical data (what the user actually sees) rather than on the DOM (which can be obfuscated; and which may change every week). | | |
| ▲ | dudhsudhd 21 minutes ago | parent [-] | | I don’t see how presenting an image would allow you to interact with the page, especially if all you are doing is modify the image you’re presenting, not the page itself. |
|
|
