large language models

A new approach applies TCP-style congestion control to route large language model requests across multiple inference providers, adjusting traffic dynamically based on how each provider is performing. The technique treats provider capacity like network bandwidth, backing off when providers slow down and routing more requests to those responding quickly. The idea is drawing attention from developers interested in more reliable, cost-efficient LLM infrastructure.

A new article traces the history of text classification methods, from early bag-of-words approaches through to modern language-model-based classifiers. The piece walks through how the field evolved, comparing classical machine learning techniques with today's transformer-based systems and explaining why newer models perform better. Readers are discussing the technical progression and what it reveals about how classification has changed over time.

MLC, the machine learning compiler project, has published TIRx Harness, an open-source compiler harness designed for agentic GPU programming, where AI agents write and optimize GPU code with compiler feedback. The announcement is drawing attention from developers interested in combining large language models with compiler infrastructure to automate low-level performance engineering.