Vol. IV · 53
The Model Already Knew the Answer — It Just Couldn't Stop Talking Long Enough to Say It
A look at a provocative new finding: two random vectors, no training, and a small open-weight model's accuracy nearly doubles.
Read entryFig. I — Filtered by tag
4 meditations tagged open models. Back toall tags or the full archive.
A look at a provocative new finding: two random vectors, no training, and a small open-weight model's accuracy nearly doubles.
Read entryKimi K3 shipped as the largest open-weight model anyone has released. This piece looks at what the compression crowd has actually managed to do about that, two days in.
Read entryFoundations · Part 8
One camp locks the recipe in a vault. The other publishes it for anyone to copy, tweak, and rebuild.
Read entryDeep Dives
Moonshot AI just shipped the biggest open-weight model anyone's ever released, and it's not just big for the sake of being big — there's real engineering under the hood.
Read entry