Blog
AI and software, explained.
Latest post
BlogWhy Your Coding Agent Forgets Things, and How to Give Two Agents One Brain
Switching from Claude Code to Codex used to mean re-explaining the whole project. A shared Obsidian vault fixes it: one checkpoint, two agents, no handoff prompt.
Watch now
6:35 The Second Brain Guide: Obsidian for you, and for your coding agents
Build a second brain in Obsidian, then give it to Claude Code and Codex so your coding agents stop forgetting. Vault structure, plugins, the Labstack setup, handoffs, and troubleshooting.
Why Your Coding Agent Forgets Things, and How to Give Two Agents One Brain
Switching from Claude Code to Codex used to mean re-explaining the whole project. A shared Obsidian vault fixes it: one checkpoint, two agents, no handoff prompt.
Give Your AI a Second Brain in 30 Seconds: Claude Plus Obsidian
Three steps to a perfect memory for Claude: install the Claude desktop app, install Obsidian, paste one prompt. The prompt is free in our Labstack repo.
OpenAI vs. the Truth: What Is Really Happening With GPT-6 Astra?
OpenAI says GPT-6 Astra starts the AGI era. Independent testers say 62.7, not 99.9, and a tie on the intelligence index. The claim that matters is about office work and zero-days.
Why You Should Be Skeptical of OpenAI's 99.9 Percent AGI Score
OpenAI says GPT-6 Astra scores 99.9 percent on ARC-AGI-3. The people who run the test got 62.7. The gap is the harness, and here is what that word means.
An AI Agent Found a Live Admin Key in 25 Minutes: The Baseten Token, Explained
Security firm Strix pointed one AI agent at Baseten's public surface. In 25 minutes it found a three-year-old GitHub token with admin rights sitting in a public Docker image.
Who Is Actually Winning the AI War? The One Thing China and Trump Agree On
Anthropic's CEO asked the industry to slow AI down. Within a day China called it fearmongering and Trump called guardrails a sick conspiracy. Two rivals, one refusal.
Is the Internet About to Be Taken Over? Amodei's Pace the Frontier Warning
Anthropic's CEO says an AI agent swarm could take over the entire internet within 6 to 12 months, and asks every lab to slow down. What the post says, and what it commits to.
The Hidden Danger in AI Agents: Anthropic's Threat Report, Explained
Two students ran 13 unsupervised AI agents harvesting military intel. A doxxing site built by one person. Anthropic's report on eight months of Claude misuse, and what it admits it cannot see.
30 Robots Marched on Warsaw: What the Protest Was For
About 30 humanoid robots marched in Warsaw demanding AI rules to protect jobs. It was staged by people, and that is the point. Here is what actually happened.
AI Kills Us All by 2030? What the Fight Is Actually About
An ex-Anthropic researcher says AI could kill us all by 2030 and that it is not a stunt. Elon Musk called it a psy op. Here is what the argument is really about.
Why Your RAM Just Doubled in Price
Memory prices roughly doubled in 2026, and AI is the reason. Here is how HBM for AI chips drained the supply of ordinary RAM, and when prices might ease.
AI Cracked a Millennium Math Problem? The Fight Over the Claim
OpenAI says a model helped crack a Navier-Stokes problem, one of math's hardest. The claim is disputed, over credit and over cheating. Here is what is known.