SecondSourceJudgment rebuilt from primary sources
Research · Aug 24, 2026

Two things you can lift straight out:

Model watch

From the Aug 24, 2026 daily brief

one, measure the cache hit rate before you look at throughput — once the hit rate collapses, every throughput number after it is wasted arithmetic. Two, if you want main-memory offload, main memory has to be substantially larger than the GPU's cache capacity, because the design copies on write: every entry written into GPU memory is written into main memory at the same time. Too small and you have effectively not enabled it. The measurer suggests 1.5 to 3 times, though the original does not explain how either end of that range was derived. ⚠️ Both come from today's single-source measurement, with no third-party re-run. Separately, the academic papers we swept this week held nothing new worth its own item, so this column has nothing new for you this issue — we do not dress an evergreen concept up as news.

Subscribe free — first issue lands tomorrow morning

Just an email address, unsubscribe anytime. This is the only thing we ask of you.

More in this section