sergio

sergio

Code agents work best in Elixir because it’s a functional language with minimal implicit configurations and conventions.

The code you see is what is happening.

Today in a Rails backend the AI was having a really tough time. Too much magic. If whatever convention you’re relying on is not in the training data, or can’t be easily inferred, the AI will really struggle writing the code properly.

#ai

Showing Posts 1 to 1

FlyingNoodle

FlyingNoodle

I think this is true for many OOP based languages/tools.

Also compilation is a huge boon for LLMs because they get a much faster feedback loop.

— All posts loaded —

Where Next? Top

Trending in AI / LLMs Top

AstonJ
This showed up on my feed.. anyone heard of it? Just hype? Ox Alpha is a reasoning model designed for coding, sustained ag...
New
sergio
It’s not that it’s vocabulary is too advanced. It’s something worse. I get lost trying to follow even a paragraph written by Claude. It’...
New
AstonJ
With advancements in AI gathering pace and set to increasingly accelerate, perhaps it’s worth having an annual thread on the topic - feel...
New
dmitriid
What A larger rant at in this post. Code at github: GitHub - dmitriid/llamex: Credo Plugin that detects issues that LLM-assisted Elixir r...
New

Other Trending Topics Top

garrison
Hobbes is a low-level distributed database for the Elixir programming language. Hobbes provides a simple, safe, and scalable storage lay...
New
mcass19
ExRatatui lets you cook up rich terminal UIs in Elixir, powered by Rust’s ratatui via Rustler NIFs. Build interactive terminal applicatio...
New
Damirados
Hello everyone. After busy few months I am happy to announce v0.1.0 of Emerge & Solve. They are GUI (Emerge) and State management (S...
New
netoum
Corex is an accessible, unstyled UI component library for Phoenix that integrates Zag.js state machines using Vanilla JavaScript and Live...
New
wintermeyer
There are three potential reasons for members of this forum to have a look at https://vutuv.de You are tired or annoyed of LinkedIn. Yo...
New
webofbits
Aludel - LLM Evaluation Workbench Aludel is an embeddable Phoenix LiveView dashboard for evaluating and comparing LLM prompts across mult...
New

We're in Beta

About us Mission Statement

Options

Thread Display Mode




Thread Preview

Skip Thread Previews