Mattt introduces Swift packages for speech and typed decisions

What changed

Backend requirements, output features and model licences vary.

Source: Mattt AnySpeechRecognizer and AnyDecisionModel announcement

Our analysis

Builder’s view: for permitted test clips, save both the transcript and the route before switching backends. Review where the route changed, so a speech error is not mistaken for a classifier regression.

Keep in mind

Local decision confidence measures probability concentration, not correctness. The author’s speech tests used macOS 27, not iPhone; AnyDecisionModel’s CoreAI trait currently conflicts with AnySpeechRecognizer.

Source: Mattt AnySpeechRecognizer and AnyDecisionModel announcement