All the latest on developer tools, open source, and building software.
Five years ago, being a dev meant knowing syntax. Today? AI writes the boilerplate in seconds. The skill that matters now is knowing what to build, how to stitch systems together, and why the elegant solution will bite you in six months. If you're still measuring yourself by lines of code shipped, you're optimising for the wrong metric.
Peter Steinberger built an open-source agent framework that lets AI actually do stuff instead of just chat. OpenAI hired him on Feb 15, 2026. Now the question isn't 'what can your chatbot say' but 'what can your agent ship.' Also: security is about to become everyone's problem.
Most teams use AI to ship faster. That just gets them to the wrong place quicker. Here's how to use AI as a thinking multiplier, not a speed hack, turning rapid prototyping into rapid learning with minimal waste.
Stack Overflow published how MCP authentication should work. I scanned 518 production servers to see what they actually do. Spoiler: 156 servers let anyone call tools that post tweets, trigger CI/CD, and send emails. No token required.
Austrian dev ships weekend project in November 2025. By February 2026: 200,000 GitHub stars, 42,000 exposed instances, 1,184 malicious packages, and a one-click RCE. Then OpenAI hired him. This is what happens when AI agents grow faster than their security model.
OpenClaw went from weekend project to OpenAI acquihire in three months. In between: 1,184 malicious packages, 42,000 exposed instances, and the fastest supply chain attack in open source history. This is what happens when AI agents grow faster than their security model.
Alibaba's open-source AI models now power 80% of new American startups, according to a16z. While the US restricted chip exports, China just shipped better software. The paradox: export controls worked perfectly on hardware, failed completely on AI.
Anthropic's Claude Cowork costs $100-200/month and runs entirely in the cloud. I built the same thing on a gaming laptop for pocket change per run. The trick: route 80% of your workload to free local models, pay cloud rates only for the synthesis stage that actually needs frontier intelligence.
Anthropic launched Claude Cowork. The market freaked. Meanwhile, I've been running similar agentic workflows from a gaming laptop for near-zero marginal cost. The secret? Not every AI task needs a frontier model.
Yannick Dixken found a critical vulnerability exposing divers' personal data. The organization's response? Legal threats and an NDA demand. Eight months later, users still haven't been notified. This is why responsible disclosure is dying.
Yannick Dixken responsibly disclosed a critical vulnerability exposing minors' data at a diving org. Their response? Legal threats, NDAs, and eight months of silence about user notifications. This is why we can't have nice things in security disclosure.
Spent three days with InfiniteTalk instead of $1,100 on HeyGen. The result: unlimited-length talking videos that run entirely on local hardware. No API calls, no usage logs, no content moderation watching what you build.