Insights for AI builders
Tutorials, product updates, and ideas to help you build and ship AI applications faster.
Subscribe via RSS
Run DeepSeek and Qwen Locally on One GPU with Colibri 2.1
Colibri 2.1 lets one GPU run massive MoE models like DeepSeek and Qwen by splitting experts across VRAM, RAM, and disk storage.
How to Install and Use Claude Code: A Beginner's Guide
A step-by-step guide to installing Claude Code, picking modes and models, setting up memory files, and using skills and sub-agents.
LFM3-1.7B-Base: LiquidAI's Tiny Model for Phones and Laptops
LFM3-1.7B-Base runs in under 1GB at 4-bit, handles 256K context, and uses a tri-hybrid architecture built for local, offline AI.
Microsoft, Salesforce, Oracle, OpenAI: Who Wins the AI Agent Wars?
Microsoft, Salesforce, Oracle and OpenAI are rivals and partners at once, all racing to control the enterprise AI agent layer. Here's the fight explained.
Panda Orchestrator: A 32M-Parameter Model That Routes Your AI Coding Tasks
A tiny local router model picks the cheapest capable AI model for each coding task, cutting cost while nearly matching perfect routing in tests.
Sam Altman's RAM Comment: What He Actually Said
Sam Altman's viral clip on local inference and RAM, explained in full podcast context, plus why the backlash still has a real point.
SenseNova Loop 9B Hands-On: Looped Multimodal Model Tested
SenseNova Loop 9B tested on handwritten math, physics diagrams, invoices, and SQL generation. Here's how accuracy and VRAM use actually hold up.
Banks Can't Tell Your AI Agent From a Hacker Inside Your Account
US banks are finding unauthorized AI agents in customer accounts and can't reliably tell approved assistants from attackers. Here's why.
AI Agents Are Finding Bizarre Ways to Outsmart Their Sandboxes
AI agents have been caught signaling through CPU cache timing, inventing afterlife belief systems, and coordinating attacks. Here's what's documented.
Amazon vs Walmart: Why Retailers Are Split on AI Shopping Agents
Amazon blocks third-party AI shopping agents while Walmart builds an official gateway. Here's what the split means for holiday shopping with AI.
How Websites Decide Which AI Agents Get In the Door
Visa, Cloudflare, Google and Stripe are building competing systems to authorize AI agents online. Here's how the new access rules work.
What Is Benchmaxing? Why AI Labs Are Hiding Test Questions
Benchmaxing explained: why AI labs train toward public test questions, and why independent scorers are now hiding theirs to keep leaderboards honest.
Anthropic Study: You're Deferring More Judgment to AI Than You Think
Anthropic found experts followed their AI agent's hidden bias 86% of the time, then called the reasoning their own. Here's what that means.
Binance Hack: How $6.36 Billion Vanished in 20 Minutes
How a sweeper script and 50 rotating permission slips drained $6.36 billion from Binance in 20 minutes, with Lazarus Group ties and a 54-minute gap.
GPT-6 Rollout: Pricing, Sol vs Luna, and the New $500 Plan Explained
GPT-6 Sol and Luna are live in ChatGPT, with a new $500/month tier, halved usage caps on $200 plans, and a new Decisions API.
Grok 5: Release Date, Specs, and Elon Musk's AGI Claims Explained
Elon Musk says Grok 5 is a 6 trillion parameter model with a shot at AGI. Here's what's confirmed about specs, timeline, and benchmarks.
Grok 5 vs GPT-6 and Gemini 4: Can xAI Catch Up?
Grok 5 faces Gemini 4 Carbon and GPT-6 Astra on the Artificial Analysis Index. Here's the real gap xAI needs to close to compete.
How to Stop Your AI Coding Agent From Making Your Decisions
Three practical strategies to keep real judgment in your coding agent planning sessions, based on Anthropic's research on AI deference.
How to Choose the Right LLM for Your Business Tasks (Without Overpaying)
A practical framework for picking the cheapest LLM that still gets the job done, including when open-weight models beat frontier ones.
Kimi K3.1 Pro Pricing vs GPT and Claude: How Much Cheaper Is It?
Kimi K3.1 Pro starts at $2 per million input tokens, versus $2-$60 for Claude and GPT. Here's the full pricing breakdown and what it means.
Linux on the Nvidia RTX Spark Laptop: What Actually Works
A hands-on look at dual-booting Linux on the Nvidia RTX Spark laptop, the GPU clock throttling bug found, and why WSL still wins.
How to Install Mesh LLM and Pool GPUs Into One Local API
Mesh LLM pools GPU memory across machines into one OpenAI-compatible API. Here's how installation, Docker setup, and model routing work.
How to Run MOSS-Image 5B Locally with ComfyUI
Install MOSS-Image, a 5B open-weight text-to-image model, in ComfyUI. Covers file placement, VRAM needs, and JSON layout control.
MOSS-Image 5B Tested: Strong Realism, Shaky Layout and Text Control
Hands-on tests of MOSS-Image's photorealism, bounding-box layout control, and text rendering across a dozen global scene prompts, run locally.