Posts

Featured Post

Dark Knowledge and the Enclosure Problem

Image
  A compression trick from 2015 became the subject of a joint NSA, CISA and FBI advisory. The path between those two facts is worth walking slowly. A thing or two about distillation! Copyright: Sanjay Basu The mythical digit Start with the experiment that named the thing. In 2015, Hinton, Vinyals and Dean trained a large net with two hidden layers of 1,200 rectified linear units on MNIST, heavily regularized with dropout and weight constraints, and got 67 test errors. A smaller net with 800 units per layer and no regularization got 146 errors. When that same small net was trained to match the soft target distribution of the large net at a temperature of 20, it got 74 errors. Half the error rate, same architecture, same parameter count, different supervision signal. Then they did the part I keep coming back to. They removed every example of the digit 3 from the transfer set, so the student had never seen a 3 in training. It still made only 206 test errors, 133 of them on the 1,010 t...
Post a Comment
Read more

The Archive Has No Statute of Limitations

Image
                                  Forgetting used to be free. Remembering was the expensive thing. Philosophy Newsletter / №XXVII / Monday, 21 September 2026 A man spent four years trying to make one page about him harder to find. He won, and became the most findable version of himself that has ever existed. I n January 1998, the Barcelona newspaper La Vanguardia printed a short legal notice. A property was going to auction to settle social security debts. The notice named the debtor, Mario Costeja Gonzalez. It was the kind of announcement that exists in order to be published and then ignored, a procedural artifact with a natural half-life of about a day. Then the newspaper digitized its back catalogue. Then Google indexed it. And a decade after the auction, if you searched his name, the notice about his debt was one of the first things you found. Not a summary of his career. Not his professional listin...
Post a Comment
Read more

Special Edition: Jev and Its Impact

Image
  What happens to the token economy when a model stops writing and starts deciding Copyright: Sanjay Basu There is a particular kind of Sunday morning that begins with two small silver boxes humming on a desk and a question. A question I am asking myself now. If the whole industry has spent three years learning to pay for tokens the way we once paid for long distance calls, priced by the minute and rationed accordingly, what happens the moment a model arrives that does not bill you for the talking at all. That was the week Jev showed up in my sandbox, and it rearranged more furniture than I expected. Let me set the scene honestly, because the setup matters as much as the model. I had two NVIDIA DGX Spark units on the bench, each carrying a GB10 and 128GB of unified memory, joined by a single QSFP cable with no switch in the middle. NVIDIA Sync did the introductions, walked the ConnectX-7 topology, planned the addresses, and exchanged keys over the fabric while I made coffee. Two hu...
Post a Comment
Read more

Installing Jev on a Two-Node DGX Spark Cluster

Image
  A TECHNOCRAT'S DISCERNMENT  ·  BUILD LOG A hands-on setup guide. Nemotron as the generator, Jev as the decision layer, TypeScript holding it together. This is the guide I wish I had on Saturday morning. We are going to stand up two NVIDIA DGX Spark units as a single cluster, serve a Nemotron model across both of them as the heavy generator, and then put Jev in front as the fast decision layer that decides what the generator ever has to see. One box would work for a smaller model. Two boxes, joined by a single cable, give us 256 GB of unified memory and the room to run a real generator at home. One point worth stating up front, because it changes how you read every step below. Nemotron runs locally on your cluster. Jev does not. Jev is TypeSafe AI's hosted System One model, and you reach it over HTTPS through the jev-code CLI or the TypeSafe SDK. So what you are installing on the cluster is the local generator, the Jev client, and the TypeScript harness that wires the t...
Post a Comment
Read more