Topic
2 articles on Multimodal, written from production systems rather than documentation.
Transcription accuracy on clean audio is a solved problem. Production audio is noisy, overlapping and full of the terms your domain depends on.
A model that describes an image accurately is not yet a system. Frame rate, cost per frame and what happens on a wrong answer decide the architecture.
Whether it needs designing from scratch or rescuing from its own success, tell me what you’re building and I’ll tell you how I’d architect it.
Open to remote and hybrid work worldwide