2 Comments
User's avatar
MB Crosier's avatar

Super interesting (and helpfully opinionated)!

I'm impressed that Gemini 2.5 is their go-to OCR tool / outperforms the custom APIs. So many existing paradigms are being disrupted just by how powerful the models are becoming.

Expand full comment
Ryan Walsh 🟢's avatar

Thanks for sharing these perspectives! One bit that really stood out to me:

> We’ve completely ignored fine-tuning. There’s an emerging consensus that it’s too time-consuming and expensive to do relative to other approaches, especially with the foundational models themselves evolving so fast. You’d have to fine tune again for every model you want to try every time a new one releases.

Expand full comment