This is a very promising idea - a model that takes arbitrary text input (which can be a complex json), plus a set of questions (yes/no, multiple-choice, or score) and quickly (milliseconds) and cheaply ($0.042/MTok) answers those questions.
Unfortunately, none of this is explained in the announcement, but the documentation [0] is pretty good.
An example with manual combinatorial exclusion in “not_for” field made me cry, this is a wild hybrid of code logic, textual definitions, and AI blackbox. It’s a cool idea, but the “glue” layer is too boilerplate-ish
maltalex · · focus · HN ↗
Unfortunately, none of this is explained in the announcement, but the documentation [0] is pretty good.
[0]: <a href="https://docs.typesafe.ai/concepts/how-to-build-with-system-one" rel="nofollow">https://docs.typesafe.ai/concepts/how-to-build-with-system-o...
leobuskin · · focus · HN ↗