If a junior is about 50% as useful as a baseline senior, and today, AI's usefulness is only slightly better than the person using it, then 50% * 75% gives you output equal to about 37.5% of a senior. The junior just ships more junior-level output; and in a complex product and complex orgs, this just ends up being a drain on everyone else.
But in the hands of a senior, 100% (senior) * 125% (ai), we get a slightly better senior.
Its not a perfect analogy, and AI is new territory with lots of surprises. AI code reviews, have been separated from the confirmation bias of the driver of the AI, _are_ where I'm seeing the greatest impact on junior engineers. These AI reviews seem to be getting things closer to a level playing field.
I see the discussions around AI in my company (big, not IT but with several large IT departments) and even our MBA IT leaders believe all the buzzwords to the letter.