> "addictive design of the algorithms"

Any self improving loop where the user is not in control, thats it.

If I subscribe to A and get more of A - thats fine.

If the algorithm detects that I spend 0.5 second longer on average looking at content with feature A and so decides to show me more of A - thats bad. At most it might be allowed to ask me if I want to subscribe to more of things with explicitly defined feature A, but even that assumes we are fine with collection of behavioural data like this in the first place and so it is a stretch already.

Transparency and control is what makes the difference here in my opinion.

Yeah I agree.

Now that would be interesting because it should actually impact the algorithms used by platforms such as Amazon...