No matter how much I carefully structure a prompt, define specific behaviors in skills, and tweak the agent md files it will still just go do something I don’t tell it to or not do something it’s got really specific instructions for. We have to write all code by LLM now at work and I’m trying to do my due diligence to review code before putting it up for PR. 9 times out of 10 when I tell it to show me a diff before committing it silently runs git diff in the background and prints “that’s the full diff”. That’s with some basic “here’s what I want when I ask for a diff” in the base context.

Nintendo Potentiometer

They Might Be Giants’ eternal wisdom: we die alone, we die afraid, we live in terror, we’re naked and alone and the grave is the loneliest place

You dropped this

All these squares make a circle

It’s an evergreen blog post, but it hits different in the age of code generating agents. Less of a commiseration in the eccentricities of writing code, more nostalgic for the before times. That could just be forced usage of those agents at work talking though

coders know computers are schizophrenic little children with auto-immune diseases

Ah ha! So it’s Russian politics!

It’s fine, that’s just blood from their nose because of the head rush from slurping the entire garden up with that courageous bite. Do not correct me, this belief is going to get me through the rest of the day