This paper introduces a novel KV cache compression method that achieves 900,000x compression ratio, surpassing TurboQuant and approaching the theoretical per-vector Shannon limit. The technique enables efficient deployment of large language models with minimal memory overhead while maintaining high accuracy.
Anthropic has introduced a 1 million token context window for its Claude Opus 4.6 and Sonnet 4.6 models, representing a significant technical advancement. The company is offering this increased capacity without additional charges to users.
Gemini 3 Pro's design capabilities and Opus 4.5's reduced babysitting needs represent a subtle but significant leap that traditional benchmarks completely miss.
The article explains how to package Perl and shell scripts for deployment on NixOS, covering dependency management and reproducible builds. It demonstrates creating Nix expressions to handle Perl modules and shell dependencies in the Nix ecosystem.
When working with 24-bit-per-pixel formats on video cards with bank-switched memory, code had to use aligned memory accesses despite the pixels themselves not being aligned. This requirement was necessary due to the hardware constraints of bank-switched video memory architectures.
llm-openrouter 0.6 adds a new "llm openrouter refresh" command that allows users to refresh the list of available models without waiting for cache expiration. This feature was added to enable immediate access to new models like Kimi 2.6 on OpenRouter.