Thread

1. warkdarrior · 1790872661 · focus · HN ↗

   Can someone explain how so many folks managed to build decision models within days or weeks after Typesafe came out with Jev? Is this concept of decision models been in the works for a while? Is it easy to copy?

   1. ramoz · 1790874435 · focus · HN ↗

      Jev created accessible/programmatic ergonomics around a general purpose classifiers, and did it very well; ie intuitive api and structured data approach.

      Anyone can copy that and apply to an array of models - stripped down LLMs or already slim/highly performant traditional classification architectures (just wrap inference with an api that inputs/outputs the same structured data).

      Jev, I think, would say their advantage is the intelligence of their models and training data including calibration: <a href="https:&#x2F;&#x2F;medium.com&#x2F;code-applied&#x2F;calibrated-classifiers-making-your-models-probabilities-trustworthy-8ccbd07c86a7" rel="nofollow">https:&#x2F;&#x2F;medium.com&#x2F;code-applied&#x2F;calibrated-classifiers-makin... (which i still struggle with in the general application... there&#x27;s no free lunch with these things).

Unofficial Hacker News client; not affiliated with Y Combinator.