I make a point of never going beyond about 220k, unless absolutely necessary (and it's almost never necessary), anyway, even with models that degrade more slowly, so this is just a discount.
--
Jesting aside, I cannot think of a single session in recent memory that used less than ~70k tokens, so I presume you are joking.
Apparently it was taken out of context or misattributed or something. Similar to "Al Gore said he invented the internet"
I've played with explorer agents giving exploration summaries to help the implementer agents use more of their context for implementation, but it doesn't work as well. There's always something lost in the handoff.