My guess, and confirmed by another comment, is that the ai only flags posts for review. Then the moderators have to manually check the post.
Honestly, it’s not a terrible use of AI in my opinion. Considering posts practically never change, they really only have to scan each post once. The mod can either flag it as safe or remove it. They are probably just running image and text pattern recognition on previously banned posts to flag newly submitted posts.
image recognition AI is notoriously bad at context, so it’ll probably flag half the nerf blasters as “potential weapons” and require human review anyway lol
Wonder how it handles nerf blasters?
My guess, and confirmed by another comment, is that the ai only flags posts for review. Then the moderators have to manually check the post.
Honestly, it’s not a terrible use of AI in my opinion. Considering posts practically never change, they really only have to scan each post once. The mod can either flag it as safe or remove it. They are probably just running image and text pattern recognition on previously banned posts to flag newly submitted posts.
Finally someone using new tech tools in a sensible and useful way .
image recognition AI is notoriously bad at context, so it’ll probably flag half the nerf blasters as “potential weapons” and require human review anyway lol
My money’s on “poorly”