Hacker News Reader

> For every new task this "AI intern" resets back to square one without having learned a thing!

I guess the author is not aware of Cursor rules, AGENTS.md, CLAUDE.md, etc. Task-list oriented rules specifically help with long term context.

Do they? I have found that with Cursor at least, the model very quickly starts ignoring rules.

You can lead a horse to the documentation, but you can't make him think.

Think is means to an end, not the end goal.

Or are you talking about OP not knowing AI tools enough?

The word "think" rhymes with "drink."

The saying is, "You can lead a horse to water, but you can't make him drink." I intended no more profound meaning than that. A quip. Nothing more.