Software engineering

Auto Added by WPeMatico

MiniMax Sparse Attention (MSA): a Two-Branch Block-Sparse Attention Trained on a 109B-Parameter MoE With a 3T-Token Budget

MiniMax released MSA (MiniMax Sparse Attention), a sparse attention method built directly on Grouped Query Attention (GQA). It targets one bottleneck: the quadratic cost of softmax attention at long context. The MiniMax research team tested it inside a 109B-parameter Mixture-of-Experts model trained with native multimodal data. They also open-sourced an inference kernel and shipped a

MiniMax Sparse Attention (MSA): a Two-Branch Block-Sparse Attention Trained on a 109B-Parameter MoE With a 3T-Token Budget Read More »

OpenAI’s Deployment Simulation Extends Pre-Deployment Risk Assessment to Agentic Coding Through Simulated Tool Calls

OpenAI published a new pre-deployment safety method called Deployment Simulation. The idea is direct. Before a model ships, simulate its deployment first. Replay past conversations through the new candidate model. Then study how it behaves in realistic contexts. OpenAI already uses insights from the method during model development. It has informed mitigations and deployment decisions,

OpenAI’s Deployment Simulation Extends Pre-Deployment Risk Assessment to Agentic Coding Through Simulated Tool Calls Read More »

🪽

Hermes Agent Adds Asynchronous Subagents, So Delegated Work No Longer Blocks the Parent Chat

Nous Research has shipped a change to Hermes Agent. Its delegate tool can now run subagents asynchronously. Per the announcement, delegated work no longer blocks the parent chat. Hermes Agent is an open-source personal agent from Nous Research. A parent agent can spawn child agents, called subagents, to fan out work. Until now, that delegation

Hermes Agent Adds Asynchronous Subagents, So Delegated Work No Longer Blocks the Parent Chat Read More »

Google Cloud Introduces Open Knowledge Format (OKF): A Vendor-Neutral Markdown Spec for Giving AI Agents Curated Context

Foundation models keep getting stronger, yet they still stall on the same thing: context. A model can write code or analyze a dataset, but only with the right internal knowledge. That knowledge includes table schemas, metric definitions, runbooks, join paths and it lives scattered across catalogs, wikis, and a few senior engineers’ heads. Google Cloud

Google Cloud Introduces Open Knowledge Format (OKF): A Vendor-Neutral Markdown Spec for Giving AI Agents Curated Context Read More »

Z.ai Launches GLM-5.2 With a Usable 1M-Token Context, Two Thinking-Effort Levels, and No Benchmarks at Launch

GLM-5.2 is the latest large language model from Z.ai, becoming the third major release in the GLM-5 line. It follows GLM-5 (February 11), GLM-5-Turbo (March 15), and GLM-5.1 (April 7). That makes four flagship-tier coding releases in roughly four months. Usable 1M-Token Context Window GLM-5.2’s standout spec is a 1,000,000-token context window. Z.ai labels the

Z.ai Launches GLM-5.2 With a Usable 1M-Token Context, Two Thinking-Effort Levels, and No Benchmarks at Launch Read More »

Claude Code Guide 2026: 25 Features with Examples + Demo

Claude Code started as a terminal coding assistant. It now runs as a layered agentic system. Underneath, Claude Code separates memory, hooks, skills, subagents, plugins, and MCP into distinct layers. Each layer changes what the model can see or do. This article covers 25 features and strategies for scaling Claude Code. It is written for

Claude Code Guide 2026: 25 Features with Examples + Demo Read More »

Databricks Open-Sources Omnigent: A Meta-Harness That Composes, Governs, and Shares AI Agents Across Claude Code, Codex, and Pi

Databricks released Omnigent, an open source ‘meta-harness’ for AI agents. The project ships under the Apache 2.0 license. The Databricks AI team built it with Neon. A harness is the wrapper around a model that turns it into an agent. Claude Code, Codex, and Pi are harnesses. Omnigent sits one level above them. It treats

Databricks Open-Sources Omnigent: A Meta-Harness That Composes, Governs, and Shares AI Agents Across Claude Code, Codex, and Pi Read More »

Anthropic Disables Claude Fable 5 and Mythos 5 After US Government Order

Anthropic has disabled its two most capable models for every customer. The shutdown followed a US government export control directive. The order arrived on June 12, 2026. It named Claude Fable 5 and Claude Mythos 5 specifically. Both models had launched only three days earlier, on June 9. The directive cited national security authorities, according

Anthropic Disables Claude Fable 5 and Mythos 5 After US Government Order Read More »

Moonshot AI Releases Kimi K2.7-Code: a Coding Model Reporting +21.8% on Kimi Code Bench v2 Over K2.6

This week, Moonshot AI released Kimi K2.7-Code. It is a coding-focused, agentic model. The model weights ship on Hugging Face under a Modified MIT license. You can also reach it through the Kimi API and Kimi Code. K2.7-Code targets long-horizon software engineering, not general chat. It plans, edits, runs tools, and debugs across many steps.

Moonshot AI Releases Kimi K2.7-Code: a Coding Model Reporting +21.8% on Kimi Code Bench v2 Over K2.6 Read More »

↗

Moonshot AI Launches Kimi Work, a Local Desktop Agent Reportedly Running on Kimi K2.6 With a 300-Sub-Agent Agent Swarm

Moonshot AI has introduced Kimi Work, an AI agent that runs on your own desktop. The Beijing-based AI entity announced it this week along with downloads for macOS and Windows. Kimi Work reads local files, drives your real browser, and runs scheduled tasks. It targets knowledge workers whose bottleneck is access to files and live

Moonshot AI Launches Kimi Work, a Local Desktop Agent Reportedly Running on Kimi K2.6 With a 300-Sub-Agent Agent Swarm Read More »