Hacker News

Why aren't languages/frameworks offering retrained models for their project?

Hacker News - Sun, 06/07/2026 - 8:32am

The cost of training is coming down.

We have incredible open source models (especially smaller ones) like qwen 3.6-27b.

Imagine the more niche languages/frameworks getting a model rebuilt for them: zig, haskell, elixir/ash, f#, IHP, jetzig, etc.

I could imagine that there would be tremendous value in a language + framework model like: zig + jetzig that is explicitly trained on the materials and best practices for these.

Which begs the question - at what point does it make sense to make a model specifically for narrower and narrower contexts. How much faster/better could they become?

Comments URL: https://news.ycombinator.com/item?id=48434185

Points: 1

# Comments: 0

Categories: Hacker News

How to Train Your Goblin

Hacker News - Sun, 06/07/2026 - 6:47am

Article URL: https://goblins.mchen.workers.dev/

Comments URL: https://news.ycombinator.com/item?id=48433586

Points: 1

# Comments: 0

Categories: Hacker News

Acquired.fm Carve Outs

Hacker News - Sun, 06/07/2026 - 6:08am
Categories: Hacker News

Pages