I've found this effect to be true with engagement algorithms as well, such as Youtube's thumbs-down, or 'don't show me this channel' 'Don't like this content', Spotify's thumbs down. Netflix's thumbs down.

Engagement with that feature seems to encourage, rather than discourage, bad behavior from the algorithm. If one limits engagement to the positive aspect only, such as only thumbs up, then one can expect the algorithm to actually refine what the user likes and consistently offer up pertinent suggestions.

The moment one engages with that nefarious downvote though... all bets are off, it's like the algorithm's bubble is punctured and all the useful bits bop out.