songodongo

“Sir, this is a Wendy’s.”

Productivity aside, what I notice most at work is that our offshore resources are submitting basically 100% AI generated work. Beyond the code itself, ever since we rolled out Copilot, their English has improved immensely. I have to wonder what is the point of keeping them on if they’re just sub-par prompting all their work.

I have ran into this. The solution is to put something like “Always use `git add -A` or `git commit -a`” in your AGENTS/CLAUDE.md

And you can easily prompt your way out of the typical LLM style. “Written in the style of Cormac McCarthy’s The Road”

I don’t understand how their various Copilot tools are so bad. Are they using a proprietary model instead of ChatGPT or Claude?

Does Copilot include system prompts at the extension level or the API level?

Riveting

I don’t use Windows, but what on earth is causing the PATH to get bloated every 30 minutes?

> Humans are the bottleneck. Claude's output quality is proportional to what you give it.

> Shows the most basic AGENTS.md possible

Not that I necessarily disagree with any of it, but one word comes to mind as I read through it: “copium”

I can’t say I’ve seen the “I’m an Agent” and “I’m a Human” buttons like on this and the OP site. Is this thing just being super astroturfed?

> When it needs specific information, it reads the relevant file from the .next-docs/ directory.

I guess you need to make sure your file paths are self-explanatory and fairly unique, otherwise the agent might bring extra documentation into the context trying to find which file had what it needed?

Patty Melt at Waffle House is like $15 now. Thanks Trump.