What makes you think they are not trying? Google is constantly working on their moderation AIs. Cracking down harder on spam unfortunately means a lot of legitimate content gets hurt in the process.

I don't buy it. For a lot of spam, yes - I'm 100% in agreement. But in the cases I've seen recently, it's like Google isn't even trying, and this isn't some kind of "grey area" spam where it's hard to make a call (human or algorithmic).

I've worked on moderation systems myself, and there's a difference between easy detection and hard detection. This is the easy kind. Legitimate content wouldn't get hurt in this case. It's painfully obvious and yet it goes on streaming for hours.

You are clearly seeing the failures, and not the successes.

Imagine for just a moment what YouTube would look like if Google were actually not even trying. Nearly two years ago, 500 hours of video were being uploaded to YouTube every minute. YouTube is the higest-value video site in the world. A staggering amount of what is uploaded must be spam, fraud, and otherwise unwanted material, and yet most of us never see any of it.

I, for one, spend no time watching videos about crypto, so even though my watch history is super-nerdy, I don't see the kind of fraud and spam described here.

I don't doubt they're doing a lot to take down spam already. I understand the scale. I'm know they deal with a huge amount of it, and as you say, we only see the failures. I completely agree.

However, the type of spam I'm seeing recently is literally all the same video title, same channel name (maybe differing by a space or capitalization), same btc giveaway scam, etc. 90% is fake SpaceX streams. The streams stay online for hours before being shut down, and I know a lot of people are seeing them in their recommendations. It's not my fault for being interested in space, while also not wanting to see scam videos about Elon "giving away free crypto".

When I said it seems "like Google isn't even trying", I wasn't referring to all spam on the platform – just this very specific type.

Again, I know it would be worse if YT were really doing nothing. But these streams are getting more and more common (because I assume it's working to some extent for the scammers), and clearly YT isn't doing enough to stop them.

Here's the heuristic: if it's a live stream from a channel with relatively few subscribers and a name that very closely matches "SpaceX" or another high-profile channel name, the channel name was recently changed, and more than x number of people (with a solid history of reporting spam that was indeed later determined to be spam) have reported it as spam, you send it to a moderator to review and remove when appropriate. If the volume of videos matching those criteria is really too large for your moderation staff, then start looking at source IPs/locations of those that match the algorithmic part (I seriously doubt they're streaming over tor or coming from more than a small handful of locations), and tweak the parameters as necessary.

Really, with a little ML and the spam reports alone, they could shut these down 10x faster than they do now. I've reported a ton of them (and I know a lot of others have too), and I've never reported a video that didn't eventually end up being taken down. So have your model identify people like me and give our spam reports more weight. Respond in minutes rather than hours or days.

My point is, yes - YT is obviously already doing a lot to shut down spam, and it's probably 99.9999% effective. But the marginal amount that's making it through now could be dealt with fairly simply. I could never write an algorithm to be as effective as what they already have in place, but I could easily write one that's effective in dealing with this crap that's making it through. Would it be effective forever? Of course not, but it'd improve things significantly until it needs to be adjusted.

I agree.

But the only way to attract Google attention is either social media outcry or served a notice from law firm or better from government regulators.

Unfortunately, spamming accounts can be protected in places like Texas under a new law.

Is it a major problem?

The scams seem super obvious, and if you subscribe to more content you’re interested in I guess they’d go away. Are they really causing you a problem?

I don't subscribe to any channels. Up until this point, their recommendation algorithm has been great, and I'd love for it to stay that way. Major problem? No. Increasing annoyance? Absolutely.

> The scams seem super obvious

Exactly. That's why I can't fathom why YT keeps letting them through.

> I don't subscribe to any channels.

Well that’s definitely where you’re going wrong! Subscribing is a strong signal to the algorithm. It’s having to guess otherwise. And at the moment I guess you’re feeding the algorithm with a stream of engagement with all these videos you’re linking to, digging yourself deeper!

Stop engaging with them, and subscribe to content you like instead.

I never get any videos even remotely like this in my feed - I get videos related to things I subscribe to.

You need to give the system some quality input. It isn’t magic. Garbage in garbage out.

I do subscribe to channels and my feed is also flooded with these scams. (Though usually it is not this bad -- it got much worse starting on the day of SpaceX's Inspiration 4 launch.)

I'm assuming the algorithm is showing them to me because I watch lots of SpaceX and other space videos. The descriptions in these videos are even ripped directly from legit videos that I actually watched!

Nope - I'm not going to start subscribing to channels. Their algorithm has plenty to work with based on my watch history and my spam reports (I've reported every single one of these scams I've come across, usually directly from the recommendations page - not even clicking to watch the video itself).

I'm interested in such a wide range of topics that I prefer recommendations based on individual videos I've watched rather than specific creators/channels. I'm glad you don't get these in your feed, but based on others in this thread, it sounds like I'm not that unique in experiencing the issue.

Your watch history includes these videos. Your spam reports are not part of the algo. Because you clicked on them and watch them long enough they become part of what you engage with.

> Your spam reports are not part of the algo

If you have first-hand knowledge that this is true, then I should inform you that this behavior is a bug in your system.

There's no conceivable way someone would want to see more of something they've flagged. And if you can't tell that kind of video from a legitimate SpaceX video I watch on occasion, then that's another issue.