news
Granite 4.1 is IBM's open-weight LLM) family released in April 2026 under the Apache 2.0 License. It is a deliberate retreat from the MoE) direction taken by Granite 4.0, returning to a decoder-only dense transformer design with no expert routing, no sparse layers, and no extended reasoning chains.
news
Kimi K2.6 is an open-source LLM) from Moonshot AI, released in April 2026. It is the successor to Kimi K2.5 and is positioned as an open-weight frontier model for long-horizon, agent-style coding and tool use, competing directly with Claude Opus 4.7, GPT-5.4, and Gemini 3 on coding and agentic bench
news
🏠 User Guide / Systems / LLM Wiki System
news
April 2026 has been a big month for open-weight AI, and it's not over yet. Three releases landed back-to-back, and together they show that the AI models you can run yourself are getting MUCH more capable, MUCH faster than most people expected.
news
Qwen3.6-35B-A3B is an open-weight LLM) from the Qwen family (Alibaba Cloud), released in April 2026. Following the Qwen MoE naming convention, the model has 35B total parameters with ~3B active per token (the `A3B` suffix), making it runnable on consumer hardware via quantization.
news
Google's latest Text-to-Speech (TTS)) model (April 2026), part of the Gemini family. Focused on controllability, expressivity, and quality for developers and enterprises building speech applications. Complements Gemini 3.1 Flash Live (real-time dialogue) with higher-quality, more controllable offlin
news
Google's highest-quality audio and voice model (March 2026). Designed for natural real-time dialogue with improved precision and lower latency. Part of the Gemini model family.
news
Auto mode is a permission mode in Claude Code where Claude makes permission decisions on behalf of the user, with a background classifier reviewing each action before it runs. It sits between the default mode (approve everything) and `bypassPermissions` / `--dangerously-skip-permissions` (approve no
news
- Course correct early and often: cancel whatever Claude is doing and adapt your prompt whenever needed - Use `claude --continue` to continue your last conversation - Use `/clear` to keep the context "clean" (focused) - Use `/add-dir <new dir>` to work with multiple directories in a single session -
news
Claude Opus 4.7 is the Claude Opus model released by Anthropic on 2026-04-16. It was the frontier model for long-running agentic work until Claude Opus 4.8 (released 2026-05-27) succeeded it, with stronger instruction adherence, self-verification, and cross-session context handling than Opus 4.6.
news
Google's "Skills in Chrome" (April 2026) lets users save frequently-used prompts as reusable one-click workflows inside Gemini in Chrome. A Skill is a saved prompt that can be re-applied to the current page and any selected tabs, turning repeated AI tasks into named, editable tools.
news
Here's a list of the AI Agent Skills I've created & published. I have many more, but these are the ones I've decided to publish as individual & reusable skills on GitHub.
A clear roadmap to building your own knowledge system. Subscribe and get it straight to your inbox.
6,000+ readers. No spam. Unsubscribe anytime.
