Tencent has released AngelSpec, an open-source torch-native framework for training speculative-decoding draft models across six architectures. It introduces DFly, a block-diffusion drafter with hybrid target conditioning…
Marktechpost AI has released Token Saver, an open-source MCP extension for Claude Desktop that uses local Hybrid RAG to slash PDF token consumption by up to…
Moonshot AI has open-sourced MoonEP, an Expert Parallelism (EP) communication library for distributed Mixture-of-Experts (MoE) workloads. The team announced the release as a library built to…
Three terms now compete for the same line in AI engineering job descriptions. Prompt engineering is the established one. Loop engineering entered the AI vocabulary in…
Liquid AI released two open-weight bidirectional encoders, LFM2.5-Encoder-230M and LFM2.5-Encoder-350M. Both carry an 8,192-token context and are built on the LFM2 hybrid backbone. The 350M ranks…
In this tutorial, we configure and operate Kimi CLI as a fully non-interactive AI coding agent. We install the CLI through uv with an isolated Python…
Fireworks AI has released Fireworks Nexus, an AI management and routing platform aimed at engineering organizations. It connects the coding tools developers already use to a…
Microsoft AI has released MAI-Cyber-1-Flash, its first model built specifically for cyber defense. It is a 137B total, 5B active sparse MoE fine-tune of MAI-Code-1-Flash with…
In this tutorial, we deploy the 1-bit Bonsai-27B language model using the PrismML fork of llama.cpp, which provides the specialized CUDA kernels required to decode the…
Moonshot AI's Kimi team and kvcache-ai open-sourced AgentENV (AENV) under MIT, as part of Kimi K3 Open Day. It runs agent sandboxes as Firecracker microVMs with…