Is this this meta-programming everyone keeps talking about. Amp — Research Preview controlling Amp — Research Preview.

What people don't realize is that most of AI is fucking boring.

Some odd things I have in most system prompts: 1. Prompt me with follow-up questions to clarify my intent. 2. Offer feedback on how I could rephrase my input or what additional information I could provide to get more accurate or useful responses. 3. Suggest possible next actions,

Time to update your Amp CLI

10 - 80 - 10 Rule: 10% writing the prompt, collecting references, bringing clarity into what I want to build. 80% let Amp code it. 10% tweak with prompts or manual edits.

New podcast episode is out with Ben Holmes on how he builds and uses Warp youtu.be/EkXimXl_0Lk

People really need to calm down.

Ya’ll Amp — Research Preview is good. Try it. Thank me later. It’s expensive but not as expensive as your time.

... and if anyone knows something about agents, it's Hamel

Our next step towards more agents in the terminal: amp -x

We work hard so you can work harder.

I am still looking for a good term for "coding with agents" Compound engineering is being thrown around by Dan Shipper 📧, but it's more in the direction of building artifacts and workflows for agents to follow. Agentic coding just feels off. Agent-Based Development, just no.

1. Wall pike shoulder openers (feet on box, chest to wall, 30 s) Just got this exercise suggestion by o3. Can someone explain to me how to put the chest to wall and my feet on a box.

Obviously, if you just got hit by a balloon filled with water, and you're like "who was that", you can click here to read it: registerspill.thorstenball.com/p/joy-and-curi…

High signal

Rust, Zig, Mojo, I just can't decide.

Hamel wasn't kidding. I've been trying Amp — Research Preview head to head with Claude Code and it is at least as good. Very bullish on this project.