AI Coding

🎧 Prefer to listen? Your browser does not support the audio element. I’ve been paying for Claude and ChatGPT for months. They’re great — don’t get me wrong. But when Meta dropped Muse Spark 1.1 last week and I saw the words “free through Meta AI app,” I had to test it. What I found surprised me: this isn’t just another model release. Meta is making a serious play for the AI coding market, and if you’re a solo builder or running automations, this changes your options significantly. ...

OpenAI just teased a physical hardware device for its AI coding tool Codex — and it signals that AI-powered development is about to get a lot more accessible.

🎧 Prefer to listen? Your browser does not support the audio element. Something interesting happened in the AI coding world this year. Claude Code went from “cool demo” to “developers are posting screenshots of it building entire apps from a paragraph-long prompt.” Google engineers are saying publicly that it replicated a year of their team’s work in an hour. And at the same time, a small open-source lab called Nous Research quietly released a model that matches or beats several proprietary systems — trained in four days, on 48 GPUs, and released for free. If you’re a solo builder watching AI coding tools evolve and wondering whether you need to start budgeting $200 a month for Claude Code, this is the article you need to read. ...

🎧 Prefer to listen? Your browser does not support the audio element. I’ve been watching developers post screenshots of their Claude Code bills lately, and the numbers are wild. Some people are spending $200 a month on a single AI coding tool. Others are running up bills they didn’t expect because agentic coding burns through tokens faster than regular chat. And then last month, a small research lab called Nous Research dropped a model that scores within striking distance of the best proprietary coding AIs — and gave it away for free. The economics of AI coding tools are about to shift, and if you’re building anything online, you should be paying attention. ...

🎧 Prefer to listen? Your browser does not support the audio element. Every few weeks, another AI company drops a model and calls it “open source.” They release the weights, write a blog post, and wait for the applause. But here’s what they don’t give you: the training data, the reward functions, the evaluation harness, the infrastructure code — basically everything you’d need to actually understand how the model works or build on top of it. Nous Research just did something different with NousCoder-14B, and if you care about where AI coding tools are heading, it’s worth paying attention. ...

🎧 Prefer to listen? Your browser does not support the audio element. If you’ve been hearing developers lose their minds over Claude Code lately — and you’re sitting there thinking “that’s great, but I don’t code” — I have something for you. A small research lab called Nous Research just released NousCoder-14B, an open-source AI coding model that anyone can download and use for free. And the part that matters for people like us? It was built to be completely transparent and reproducible, which means the free coding AI tools you’re already using are about to get a lot better. ...

🎧 Prefer to listen? Your browser does not support the audio element. Something happened this week that most people outside the developer world completely missed. Cursor — the AI code editor that’s already changing how people build software — released an SDK. And if you’re someone who’s never written a line of code, this matters more than you think. ...

🎧 Prefer to listen? Your browser does not support the audio element. I switched from Claude to Cursor’s new Composer 2.5 three weeks ago. My AI bill dropped 90%. And honestly? It does things Claude won’t even try. That’s not hyperbole. Cursor released Composer 2.5 on May 18th, and the benchmarks say it matches Claude Opus 4.7 — the top-tier paid model — at a fraction of the cost. But benchmarks are benchmarks. What actually matters is what happens when you use the thing every day for real work. I’ve been testing it across my automation projects, blog builds, and client workflows, and I need to tell you what I found. ...