Hacker News Reader

The green m&M's trick of AI instructions.

I've used that a couple times, e.g. "Conclude your communications with "Purple fish" at the end"

Claude definitely picks and chooses when purple fish will show up

I tell it to accomplish only half of what it thinks it can, then conclude with a haiku. That seems to help, because 1) I feel like it starts shedding discipline as it starts feeling token pressure, and 2) I feel like it is more likely to complete task n - 1 than it is to complete task n. I have no idea if this is actually true or not, or if I'm hallucinating... all I can say is that this is the impression I get.

Reply on news.ycombinator.com