2,281 karma · joined July 29, 2014
Because I noticed people at my work did similar requests to improve CI. The result was a faster CI, but full of cludges huge inline bash scripts in workflow YAML files, and effectively unmaintainable, unreviewable mess. After just a few rounds of these optimizations the entire CI setup is basically a Rube Goldberg machine but made of duct tape.
For example, recently I’ve been adding skills for our team. I added evals. If you ask an agent to make evals it’ll always try to bias and overfit just to make tests pass. No matter if I have it stated in every possible place not to do it and Codex instructed to catch these cases. It doesn’t work. Lots of sloppy evals get written and skills get extremely specific instructions to pass specific tests.
I think if you are implementing trivial features in a green field product it can work to some degree for some time. But eventually it’s going to deteriorate into a mess. Death by 1000 paper cuts.
I’ve had a long discussion with a coworker on a long drive.
What we came to realize is the difference in our attitude towards writing code.
I approach it as craft. Even when I’m doing 100% of my coding with an agent these days. I still care about the result to be of high quality and maintainability. I still use my system design knowledge to guide the agent to produce scalable systems.
He treats it like just a job. If it’s good enough he ships. The edge cases and bugs don’t matter. Can be fixed later.
But in my mind that’s a fallacy. We all know things don’t get fixed later unless they are obvious defects and users complain.
Instead we get slow degradation of overall quality. All those small issues compound overtime to create a brittle systems that is difficult to debug and maintain.
My mental model of software engineering is like this. Each commit/PR is a small LEGO block. If you make them well they’ll snap well and create a stable structure that can withstand forces. If every LEGO block you make is just slightly off here and there. Your structure becomes unstable and will always have faults and will always have failures under unpredictable environmental pressures.
Human body prefers ketones as a source of energy. But glycogen is faster.
My simplified mental model is like this. Ketones are normal gasoline. And glycogen is racing fuel (ethanol). If you run a stock car on racing fuel it may start and drive for a while but it’s damaging the engine and creates unnecessary wear.
But the fastest accessible energy source is glycogen, which comes from carbs.
https://www.businessinsider.com/what-foods-looked-like-befor...
Write REVIEW.md.
I have CC check itself pretty well.
I also put into agent/claude/review instructions to write using simple English skill and humanizer skill. Then not to write redundant comments.
It’s not perfect but definitely catches lots of slop.
I said back then that it was just that - engagement farming. It was clear as day that some groups like this existed. Some groups just pushed affiliate links or selling t shirts (print on demand). It was just that. Even a little digging with critical thinking was making obvious if you were on the internet long enough.
My interpretation is:
Context.dev service API key to retrieve company logo, industry, and socials for a company domain […that agent had identified]
Because my friend had the craziest protectionism story.
He wanted to build a multi family home on his existing lot.
Of course all kinds of studies need to be done. One of them is a tree study. Which costs $3,000 alone per tree. He hired firm and they were doing a study (for building purposes).
Then one day a crew shows up and cuts the tree all of a sudden. Turns out that his neighbour, unknown to him, was complaining that the tree was creating too much shade. So without any study they just came and cut it down.
That’s before even his study results came back.