pipsterwo

Totally, edited my comment to specify "based on the assumption above." The main takeaway I was going for was 0.1% is not a small number in this context

1/1000 of inference compute is a non-trivial workload at scale. Gartner estimates ~$28B in inference spend for 2026 making this a $28 million dollar per year workload (edit: based on the assumption above)

Source: https://www.gartner.com/en/newsroom/press-releases/2026-07-2...

They're making a joke using the double meaning of the word fans

Did anyone else notice the pyrotechnics in the landing feet after touchdown? I'm going to assume that they harpooned the deck surface to secure the booster.

Im pretty impressed at how simple that idea is compared to SpaceX's solution which is to have a robot drive underneath and grab the booster

They originally claimed the stainless steel panels would replace the internal frame and thus be more efficient to produce. But they shipped with a traditional frame

If it works on mac & linux I've got nothing to worry about

I find them really useful, I find youtube to be a good thing in moderation. But its very helpful to have a timer forcing me to thoughtfully use the time I've allocated.