JustVugg/colibri is a pure-C, zero-dependency inference engine by Vincenzo Fornaro that streams routed MoE experts from NVMe, running models like GLM-5.2 and Kimi K3 on consumer hardware. 51,687 stars as of 17 November 2026.
Read ArticleExplore our latest tutorials, tech updates, and career advice written by industry experts to help you level up your skills.
JustVugg/colibri is a pure-C, zero-dependency inference engine by Vincenzo Fornaro that streams routed MoE experts from NVMe, running models like GLM-5.2 and Kimi K3 on consumer hardware. 51,687 stars as of 17 November 2026.
Read ArticleSeer (arXiv:2611.26423) is an inference-time framework for small deep-research agents. The paper reports GAIA accuracy rising from 13.6% to 41.7% on Qwen3.5-4B and S32 reaching 79.6% on GAIA.
Read ArticleA trends overview of late-2026 AI algorithms — hybrid state-space–attention models, diffusion language models, learnable memory, RLVR reasoning and world models — based on Seihwan Kim's November 2026 synthesis, with corroboration noted.
Read ArticleReson8 open-sourced Rumble-2-Flash on 18 November 2026 under Apache 2.0 — a 0.5B-parameter speech-recognition model for 40+ languages, built on the Qwen3-ASR architecture.
Read ArticleEdge0 open-sourced its 145B-parameter latent sparse MoE model on 12 November 2026. The code is Apache 2.0, but the weights sit under the Edge0 Community Model License 1.0 — not Apache or MIT.
Read ArticleMIT CSAIL's "Sparks of Weight-Space Programming" (2 Nov 2026): GPT-6 Astra edited 0.016% of Qwen3.5-0.8B's weights — no training loop — and MATH-500 accuracy rose from 7.9% to 48.1%. A repair, not new knowledge.
Read ArticleAsk about courses, website & more
Request human callback:
Please log in to download. You will stay on this page after logging in!
New here? Register now →