Met someone whose agents ship more code in a week than my whole team does in a month. I asked him what actually made him this good - which loop framework, which prompt pack. He laughed and sent me a Stanford lecture. Andrew Ng - CS230, Intro to Deep... Learning. Free, an hour long. "Everyone memorizes loop tricks," he said. "Almost nobody understands the thing the loop is wrapped around." I watched it last night. Halfway through, I realized I'd spent a year duct-taping agents together without ever understanding what was happening underneath any of it. Bookmark it. Watch it today - then the loop guide below finally clicks.show more

the fix for a year of hacks is one hour of fundamentals

yep, it's base of life

truth

Entiendo que el fondo siempre pesa mas que los trucos de prompt. Eso es lo que pasa con el dinero tambien. Nos enfocamos en loops rapiditos y olvidamos los principios basicos que sostienen todo.

That’s a gold nugget drop. Catchy line: “Code moves fast, but learning faster? Stanford level.” This is the kind of cross-pollination that sparks vibes and saves teams.

turns out you can't prompt engineer your way out of knowing the math 💀

That Stanford lecture humbles even the best prompt engineers.

Makes sense that the answer was fundamentals, not a prompt pack. The people getting huge agent leverage tend to know exactly what good output looks like, so they can spot when the model is confidently wrong. Prompt tricks are downstream of actually understanding the problem.

thanks for sharing bro

welcome mate

You ONLY need one agent. 🤷🏾‍♂️ That’s all I use and I am still waiting for the industry to catch up.

That hits because it's true. Most people chase the tactic without learning the foundation underneath it. Going to watch this one tonight.