Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
An educational build log on constructing the systolic array at the heart of Google's TPU from scratch — starting with a single NAND gate and working up to a running 2×2 array in a digital logic simulator.
-
Deriving the view of softmax attention as Nadaraya-Watson kernel regression, why local constant estimators have boundary bias, and how Parallax adds a learned local-linear correction on top of softmax.
-
Why per-token recurrences are slow on GPUs, how chunkwise DeltaNet uses the WY representation, and how MQAR shows empirically the improvements of delta rule and gating in fixed-state recurrences.
-
From TTT and Titans to the four axes of MIRAS — reframing the hidden state as a tiny model trained online, and placing every modern sub-quadratic architecture (DeltaNet, Mamba2, Gated DeltaNet, TTT, Titans, KDA, ATLAS) on four design choices.
-
Showing that softmax attention and other sub-quadratic models (linear attention, SSMs, etc.) belong to the same class of models that differ in how they store, optimize, and forget memories.
-
A step-by-step guide to wiring Clerk’s polished web flows into a headless Rust CLI so users can `mycli auth login`, grab a long-lived JWT, and hit protected endpoints without sacrificing security or sanity.
-
...
-
Escaping CrystalReport.
-
From our phones to our cloud services, Europe depends on American tech.
-
How to build a modern and scalable PDF rendering service using AWS Lambda.
-
Exploring how AI and cross-modal search can revolutionize e-commerce search, moving beyond traditional text-based methods to understand visual product features and customer intent.