The case for bespoke classifiers, even now that LLMs do JSON
Frontier models return valid JSON every time. A small classifier trained on your own categories still wins on consistency, cost and ownership. Here's why.
6 min read
Models & Classifiers
Small, specialised models: classifiers, fine-tunes and speech recognition, and when a model of your own beats a general-purpose API.
Fine-tuning Whisper on Modal's serverless GPUs
A script for fine-tuning OpenAI's Whisper speech recognition models using Modal's serverless GPU infrastructure.
4 min read