100X efficiency improvement (doubtful) still means that costs grow 200X faster than benchmark performance.

Even assuming that past rates of inference cost scaling hold up, we would only expect a 2 OoM decrease after about a year or so. And 1% of 3.5b is still a very large number.

And to your point "past performance is not indicative of future results". The extrapolate to infinity approach is the mindfever of this field.