Hacker News Reader

Author here. I understand that you need to prompt in a way that is similar to training set.

It makes sense but it's still weird that your instructions to the machine needs to sound like talking to human. This is just side effect of how is the machine trained and constructed.

View on HN

Agreed that it is weird. FWIW, when I feel my chat with the LLM has landed (I got a final answer I'm satisfied with), I usually just close the tab or exit the agent session without the ceremony of "thanks, that was helpful."

Anyhow, I feel these entire chats are a gentle game of what to tell, when, and how much. Too little guidance and it won't understand the goal. Too much and it'll drown in details and lose focus. The gestures (which I do try to keep as short as possible) are micro-steerings I apply along the way.

Reply on news.ycombinator.com