Comment

Comment by rglover

Really enjoyed this! Thank you for sharing your approach and notes on process.

This framework makes a lot of sense. I think the general approach of eschewing one-shot prompts in favor of letting the LLM craft its own prompts (per your standards) is the missing piece in a lot of workflows.

parent rglover 1 year ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton