Thread

1. soerxpso · 1789847449 · focus · HN ↗

   Jev doesn't require finetuning. All of the posts claiming that the technology already existed are missing that I don't want to spend a week to create a dataset (for a problem I might not already have data for), finetune a model, and set up infrastructure to run the model, every time I have a small routing or classification problem. The ability to knock out any arbitrary classification problem in minutes instead of in a week is a big deal.

   1. m3kw9 · 1789850755 · focus · HN ↗

      This is the real moat, the training data, they even said it, it's the meticulously crafted data that they bet on

      1. bjt12345 · 1789859015 · focus · HN ↗

         Even then, TypeSafe AI point out that "Jev doesn't have deep knowledge of niche domains, but you can supply context to help it decide. If you’d like Jev trained on your use cases, let us know."

         1. m3kw9 · 1789868719 · focus · HN ↗

            This is same case with LLM's which allows you to also fine tune it.

            1. bjt12345 · 1789914740 · focus · HN ↗

               Not really. SOTA LLMs have much larger context windows.

Unofficial Hacker News client; not affiliated with Y Combinator.