The Technically Library

Finally, an explanation for why AI models can't seem to quit them.

Enough surveys and corporate hand-waving. Let's answer the question by looking at usage data from an AI compute provider.

AI models seem to approximate the brain, intentionally or otherwise.

Comparing Replit, v0, Lovable and Bolt, in a bakeoff to decide who will be Vandalay Industries go-to vibe coding tool.

A look at the thin line between using AI smartly and writing your own pink slip.

How to actually make your AI workflows, er, work.

How to make sure your next big AI push doesn't flop.

Why Three Mile Island is back in action after a 50 year hiatus.

How AI models learned to stop being weird and start being helpful.

All about AI evals, plus how Braintrust helps companies build better AI apps.

Things you should know as a vibe coder that will make your app actually work / not die.

How Vercel went from deploying apps to redefining how we build them.

How computers learn patterns from data: the foundation for everything from stock price prediction to ChatGPT.

How bigger models, more data, and more compute keep beating clever tricks.

How FastMCP makes it easy to ship an MCP server.