GLM-5.2 is the newest giant language mannequin from Z.ai, turning into the third main launch within the GLM-5 line. It follows GLM-5 (February 11), GLM-5-Turbo (March 15), and GLM-5.1 (April 7). That makes 4 flagship-tier coding releases in roughly 4 months. Usable 1M-Token Context Window GLM-5.2’s standout spec is a 1,000,000-token context window. Z.ai labels…
Claude Code began as a terminal coding assistant. It now runs as a layered agentic system. Underneath, Claude Code separates reminiscence, hooks, abilities, subagents, plugins, and MCP into distinct layers. Each layer adjustments what the mannequin can see or do. This article covers 25 options and techniques for scaling Claude Code. It is written for…
Databricks launched Omnigent, an open supply ‘meta-harness’ for AI brokers. The undertaking ships below the Apache 2.0 license. The Databricks AI group constructed it with Neon. A harness is the wrapper round a mannequin that turns it into an agent. Claude Code, Codex, and Pi are harnesses. Omnigent sits one stage above them. It treats…
In this tutorial, we implement a QwenPaw workflow that gives a sensible surroundings for constructing and testing an agent-powered assistant. We set up and initialize QwenPaw, configure its working listing, arrange authentication, join optionally available mannequin suppliers through Colab secrets and techniques, and create a structured workspace with customized abilities and native data information. We…
Anthropic has disabled its two most succesful fashions for each buyer. The shutdown adopted a US authorities export management directive. The order arrived on June 12, 2026. It named Claude Fable 5 and Claude Mythos 5 particularly. Both fashions had launched solely three days earlier, on June 9. The directive cited nationwide safety authorities, based…
This week, Moonshot AI launched Kimi K2.7-Code. It is a coding-focused, agentic mannequin. The mannequin weights ship on Hugging Face underneath a Modified MIT license. You may also attain it by the Kimi API and Kimi Code. K2.7-Code targets long-horizon software program engineering, not normal chat. It plans, edits, runs instruments, and debugs throughout many…
Google Research group has introduced the launch of Gemini-SQL2 on X. They described this method as a breakthrough text-to-SQL functionality powered by Gemini 3.1 Pro. Gemini-SQL2 posted 80.04% execution accuracy on the BIRD Text-to-SQL Leaderboard (Single Model). Google’s chart locations it above its personal Gemini-SQL, the prior high entry. The metric measures whether or not…
Moonshot AI has launched Kimi Work, an AI agent that runs on your personal desktop. The Beijing-based AI entity introduced it this week together with downloads for macOS and Windows. Kimi Work reads native information, drives your actual browser, and runs scheduled duties. It targets information staff whose bottleneck is entry to information and reside…
Perplexity has moved Deep Research into Computer, its multi-model orchestration system. The improve improves accuracy, depth of study, and quotation high quality. Deep Research now breaks onerous questions into subtasks and routes them throughout 20+ frontier fashions. It returns work-ready experiences, decks, and dashboards, all inside Computer. Deep Research in Computer Deep Research is a…
Today, xAI shipped the Grok Build Plugin Marketplace. It is a built-in catalog of plugins for Grok Build, the corporate’s terminal coding agent. A plugin bundles abilities, slash instructions, brokers, hooks, MCP servers, and LSPs into one bundle. You browse, set up, and replace these packages with out leaving the terminal. Plugin Marketplace Grok Build…