2026-07-268 saved articles | Back | Library |
|---|
| Article | Read |
|---|---|
| Causal DAG extraction from a library of books or videos/movies Determining a causal DAG (directed acyclic graph) for a problem under consideration, is a major roadblock when doing Judea Pearl's Causal Inference (CI) in Statistics. The same problem arises when doing CI in Artificial Intelligence (AI) and Machine Learning (ML). As with many problems in Science, we think Nature has found an effective solution to this problem. We argue that human and animal brains contain an explicit engine for doing CI, and that such an engine uses as input an atlas (i.e., col | |
| reactor (@reactorworld) on X Introducing OpenDreamer, an open reproduction of Dreamer4. We supported @FrancescoSacco1, @martidiegom, and @edward_s_hu to build a frontier-level world model, and we've open-sourced everything: the model, the training code, and every hard-won lesson from building it. | |
| GitHub - mocusez/triton-metal: Proof-of-Concept Apple Silicon Backend for Triton Proof-of-Concept Apple Silicon Backend for Triton. Contribute to mocusez/triton-metal development by creating an account on GitHub. | |
| GitHub - ben594/triton-metal: Apple GPU support of the Triton language and compiler Apple GPU support of the Triton language and compiler - ben594/triton-metal | |
| Spatial languages Writing code in 2D: a spatial programming language with vertical operands, quantum uncomputation puzzles, and a 3-bit adder in a single 2D expression. | |
| SIMD for Collision In a previous post SIMD Matters I discussed the big wins I got from graph coloring to make the contact solver faster. That same approach exists in Box3D. I like to call this approach “wide SIMD”. The idea is to process multiple work units at the same time. In the contact solver this means solving four contact points at the same time. This is different from “narrow SIMD” where a 3-vector (xyz) is put into a SIMD register and then standard vector math is expressed as SIMD intrinsics. | |
| GitHub - M-Abozaid/esp32-c3-adblock: Pi-hole-class DNS ad-blocker on a $2 ESP32-C3 (no PSRAM): 537k domains as 40-bit FNV-1a hashes in flash, binary-searched. UDP DNS sinkhole + web dashboard. https://youtube.com/shorts/RaxszOUMi8E?feature=share Pi-hole-class DNS ad-blocker on a $2 ESP32-C3 (no PSRAM): 537k domains as 40-bit FNV-1a hashes in flash, binary-searched. UDP DNS sinkhole + web dashboard. https://youtube.com/shorts/RaxszOUMi8E?fe... | |
| Compression and Intelligence On the relation between compression, intelligence, and LLMs. |