Most AI astrology products begin with a prompt. We chose a different architecture for OpenFate:...
Most AI astrology products begin with a prompt.
We chose a different architecture for OpenFate: calculate the chart first, freeze the structured evidence, and only then ask an AI model to explain it.
The problem with prompt-first generation
Explain the technical problems you observed:
Language models should not calculate calendrical or astronomical data
There is a genre of prompt going around: paste your birth date and time into a chatbot and ask for...
Why your AI prompts are failing and how to shift from search-based querying to structured logic for better code generation.
I spend a lot of time around astrology apps — not because I'm a true believer, but because the...
I build software in the single worst domain for LLM truthfulness: fortune-telling. A BaZi (Chinese...
Astro is built around one idea: ship less JavaScript. Islands architecture means only the interactive...
Before writing any LLM logic, define your evaluation step. Here's how evals catch bad outputs early on production systems.
