The problem with this approach is that it is easily bypassed. Simply point your camera at a high quality monitor playing an AI generated video, and there you go, and authenticated AI video. In the future, video evidence is going to be as convincing as it was for 99.9999...% of human history. We survived with out it in the past. We'll survive without it in the future.
I doubt it will be that easy to bypass. A fake would still have to withstand pixel-level analysis on the level of methods that already detect tampering in regular video. For one thing, that will have to be a very high quality monitor indeed to leave no detectable trace of e.g. moire patterns.
A fake doesn’t need to be perfect to be effective, it just needs to fool enough people. Most posts won’t (and couldn’t ever) be scrutinised at that level.
Even if a lot of people just lap up whatever tiktok feeds them, it still matters that people who care can get actual evidence from the real world that eventually filters out to public consciousness. It will have indirect influence, yes, but it'll still be a lot better than being fully post-truth.
We have been able to manipulate legal documents for 100s of years.
We have been able to manipulate images for over 100 years.
We have been able to manipulate images on any computer with a few hours of training for for 30+ years.
We have been able to manipulate videos with training for 20+ years.
It is an order of magnitude easier now (likely as easy as documents have been to manipulate for 30ish years now). However, this is not a new problem, courts have always had to deal with manipulated evidence.
Not just an order of magnitude easier, many orders of magnitude. We're going from hours of painsraking work done by professionals who you pay to virtually instant and as many as you want.
