Insights for AI builders
Tutorials, product updates, and ideas to help you build and ship AI applications faster.
Subscribe via RSS
How to Get Access to Claude Mythos Through Anthropic's Cyber Program
Anthropic's Cyber Verification Program lets vetted security researchers apply for access to restricted Claude Mythos models. Here's what that means.

Is Claude Becoming the Operating System for Business?
Anthropic is bundling sheets, docs, whiteboards and a meetings agent into Claude, turning it into a single layer over business software.

Claude Code's Code Mode: How It Replaces Tool Calls with JavaScript
Claude Code's experimental Code Mode lets Claude batch tool calls into JavaScript instead of one-by-one requests. Here's the setup and limits.

Claude Meetings Explained: Your New AI Meeting Assistant
Claude can now join video calls, take notes, build slides live, and chase down action items. Here's how Claude Meetings actually works.

How to Use Evals to Pick the Cheapest AI Model That Works
Learn how to build evals that find the cheapest AI model that meets your business requirements, before you pay for a frontier model you don't need.

LongCat 2.5: Meituan's 1.6T Model Looks Good on Paper, Shaky in Practice
LongCat 2.5 is Meituan's 1.6T parameter MoE model for agentic coding. Hands-on tests show gaps between its benchmarks and real output.

Qwen4-Max Pricing: How Alibaba Cloud's Token Plans Actually Work
Qwen4-Max pricing runs through Alibaba Cloud token plans, with entry access starting around $3/month. Here's how the tiers work.

Qwen4-Max Review: Does Alibaba's Frontier Model Beat Claude Opus 5.5?
Qwen4-Max exits preview with strong agentic coding, vision, and multilingual results. Hands-on tests against Claude Opus 5.5 inside.

How to Build a Recursive Self-Improving Agent Harness
A technical breakdown of building an AI agent harness that writes and evolves its own tools mid-task using Gemini's Interaction API.

What Is an Agentic OS? The Portable AI Workflow Folder Explained
An agentic OS is a model-agnostic folder of context, skills and memory for AI tools. Here's how it works and why it beats app-locked setups.

How to Run Alpie Seed 9B Locally with llama.cpp
Step-by-step setup for running Alpie Seed 9B GGUF locally with llama.cpp, covering VRAM needs, serving commands, and agent harness hookup.

Alpie Seed 9B Tested: Does It Live Up to Its Benchmarks?
Hands-on tests of Alpie Seed 9B show failed coding, vision, and physics tasks despite benchmark charts claiming it beats 20B and 30B models.

How to Build a Claude Skills and Projects Workflow That Runs Itself
A practical guide to layering Claude prompts, projects, skills, and scheduled tasks into one automated, repeatable workflow.

How to Become a Forward Deployed Engineer: A Practical Guide
A step-by-step guide to becoming a forward deployed engineer: finding businesses, mapping workflows, and deploying AI agents to automate them.

What Is Grok Bot? xAI's AI Teammate Tool, Explained
Grok Bot lets you build AI teammates with identities, tools, and logins. Here's how xAI built it, and how companies actually use it.

MiniMax H3 Image Tested: Text, Editing and Realism Benchmarked
A hands-on review of MiniMax H3 Image across text rendering, multi-image editing, identity preservation, and photorealism tests.

Tracer: The Free Open-Source GUI That Runs Multiple Coding Agents
Tracer is a free open-source app that orchestrates Claude Code, Codex, Cursor and other coding agents in one workspace, on desktop and mobile.

When Will AI Automate AI Research? The Timeline Explained
Why forecasters now think AI could match top AI researchers within a few years, and what that implies for superintelligence timelines.

AI and Math: From Broken Arithmetic to a Millennium Prize Problem
How AI models went from failing basic arithmetic in 2023 to winning IMO gold and solving a Millennium Prize problem by 2025.

DSpine vs DFlash2: Which Speculative Decoding Draft Model Wins?
A hands-on H100 benchmark pits Tencent's DSpine against Z-Lab's DFlash2 on Qwen3.8-27B, comparing real tokens-per-second results.

Edge0-145B Benchmarks: Terminal-Bench, GPQA, HLE, and IFBench Explained
Edge0-145B's NVFP4 build hits 86.5 on Terminal-Bench 2.1. Here's how it stacks up on GPQA-Diamond, HLE, and IFBench, and the NVFP4 vs Q3_K tradeoff.

Edge0-145B: How a 145B-Parameter Model Fits on One RTX 5090
Edge0-145B packs 145 billion parameters into 24GB VRAM using native 4-bit quantization and a sparse MoE design. Here's how it works.

Edge0-145B NVFP4: A 145B Agent Model on One RTX 5090
Edge0-145B is a 145B-parameter sparse MoE model quantized to NVFP4, built to run locally on a single 24GB consumer GPU for agent tasks.

GPT-6 Cyber: Why OpenAI Built an AI It Won't Let You Use
GPT-6 Cyber found hundreds of real exploits and dozens of Firefox bugs, but OpenAI locked it to approved security teams only. Here's why.