News for hackers. Stuff that matters.
Re:Next.js 16.4 by desireco42 on Saturday October 10, 2026 @01:59AM (#50030061)
Shame but also opportunity... These apps will not be good, they will look good and appear to work, but then... they will need to be rewritten.

I am often posting that if you pick Gleam for UI, Rails or Phoenix, which will make your codebase easier to follow and more stable, I will give you discounts.

Re:Next.js 16.4 by Imustaskforhelp on Saturday October 10, 2026 @02:26AM (#50030230)
Gleam as a language is genuinely underrated for porting.

I had made a Golang htmx + templ codebase and just out of curiosity I ported it onto gleam using an open weights model (glm 5.3)

Although it struggled a little bit first because of learning some parts of gleam but overall after it searched for documentation and learnt some things on its own, it was able to completely rewrite it in just 1/2 very small prompts which is crazy.

I think phoenix can be great as well and I am doing an experiment to try to port it to many functional languages and just testing which language is the best for it but so far I am impressed by gleam!

Re:Next.js 16.4 by desireco42 on Saturday October 10, 2026 @12:12PM (#50034300)
Yeah my agents do spend a little bit more time with it, and I use GLM Flash mostly. Gleam has good error messages which helps a lot. But once they write something it is much more solid.
Re:Next.js 16.4 by Imustaskforhelp on Saturday October 10, 2026 @12:31PM (#50034493)
Yea, I think that for AI, good error messages might just be worth their weight in gold.

I was just trying to port the same website to elixir and I am finding that there are issues within it and also for some reason the agent got stuck at something and then it started writing elixir within the repl and doing something related to ecto.

In my current experience, contrary to what I would've expected (given that elixir is a more mature language than gleam), gleam is surprisingly better, though I will try to do more tests

Some other thoughts that I am having at the moment is that starting a project in gleam or within sveltekit/astro/solidjs and then porting it to gleam can be great if what you are doing is frontend heavy. AI will take time once to learn gleam but then the rewrite becomes much more solid and personally interesting to me

Looks like I have to learn gleam to see how fun & managable the codebase can be :-D