I've built multi-agent systems for clients. I still think they're overrated for most use cases. What's underrated is boring. Context compaction. The reason your AI app feels slow and expensive isn't the model. It's everything you keep stuffing into the prompt before it even
@whats_ai
-
AI generates average posts, not your unique take
By
–
When you ask AI "write me a post about X", the model doesn't think about your audience or what you want to say. It just picks the most likely next word from millions of examples it was trained on. You end up with the average of every other post on that topic. Not your take.
-
Caveman talk with Claude saves 75% on AI costs
By
–
I started saving 75% on AI costs by telling Claude to talk like a caveman. Sounds dumb. It's actually a real technique. Why use long sentence when short one work fine? Here's how it works. Every time you send a message to Claude, the model rereads the entire conversation
-
AI image generators don’t paint pixel by pixel like digital artists
By
–
You probably think AI image generators paint your image pixel by pixel, like a digital artist filling in a canvas.
That's not what's happening. A normal image has millions of pixel values. Generating those one at a time would be too slow and too expensive. Even on the best GPUs. -
Why larger context windows can degrade AI agent performance
By
–
After a long 2-week vacation, here's finally a new video! Let's finally explore why bigger context windows make your agents worse, and, as a bonus, 10 context management techniques that actually work! Watch it here: https://
youtu.be/PQglg4N_jxo -
The Evolving Role of Developers in the Age of AI Agents
By
–
Developers don't get paid just for coding! If your only skill is writing code, an agent can do that for $20 a month. And it will only get cheaper from here. Who gets paid now is the developer who knows what to build, what to skip, and what to fix when an agent silently gets
-
Impact of Bad Prompting on AI Agent Performance
By
–
That’s exactly what bad prompting does to your agents.
-
Distinguishing between ML Engineers and AI Engineers
By
–
You don't need to learn about machine learning in depth to become an AI engineer.
I know this goes against a lot of advice online, even some of my own. But ML engineers and AI engineers are two different roles now. An ML engineer works inside the model. Training pipelines, loss -
Distinguishing Between Agentic Coding and Vibe Coding
By
–
Agentic coding isn't vibe coding with a better name.
People use these two terms interchangeably, but they are not the same thing. Vibe coding is when you let Claude or Cursor write code for you and you ship it without reading a line. Fast, fun, often 80% there. And almost never -
Understanding Recursive Self-Improvement in AI
By
–
If you want to learn how recursive self-improvement works, I break it all down in 14 minutes here: https://
youtu.be/ky1TkRWA65M?si
=pf9w9LQyzXv4VXOe
…