-
Gradient descent variants on one loss surface: momentum, RMSProp, Adam visualized
Imagine four hikers trying to reach the bottom of the same mountain valley. Each can measure the slope beneath their feet, but none has a complete map of the terrain.
-
Speculative decoding and other tricks that make inference 2x faster
A modern large language model can process thousands of input tokens in parallel, yet generating its response still involves a surprisingly inefficient process: producing one token at a time.
-
This is not an ML problem: constraint solvers with OR-Tools CP-SAT
Imagine you’re building a scheduling system for a fulfillment center.
-
Topics Everyone Is Talking About No415
One Week Using Codex More Than Claude • New Model Context Protocol Roadmap • A Kantian Critique of Justin Biebers Sorry • The Cool Ideas Behind Gleam • PiKVM Adds Webcam Forwarding Support…
-
Topics Everyone Is Talking About No323
Dear ACM: Youre Using AI Wrong But Theres Still Time to Fix It • Partial Inlining: Smarter Compiler Optimization Explained • Mastering Bit Arrays in Gleam • GPT-5.2-Codex • Inside Chinas Manhattan Project for AI Chips