It's clear that AI assisted coding is dividing developers (welcome to the culture wars!). I've seen a few blog posts now that talk about how some people just "love the craft", "delight in making something just right, like knitting", etc, as opposed to people who just "want to make it work". As if that explains the divide.

How about this, some people resent the notion of being a babysitter to a stochastic token machine, hastening their own cognitive decline. Some people resent paying rent to a handful of US companies, all coming directly out of the TESCREAL human extinction cult, to be able to write software. Some people resent the "worse is better" steady decline of software quality over the past two decades, now supercharged. Some people resent that the hegemonic computing ecosystem is entirely shaped by the logic of venture capital. Some people hate that the digital commons is walled off and sold back to us. Oh and I guess some people also don't like the thought of making coding several orders of magnitude more energy intensive during a climate emergency.

But sure, no, it's really because we mourn the loss of our hobby.

@plexus You don't have to use big tech to have a coding assistant. Run it locally. Been using #OpenCode over the last few days.
https://opencode.ai/
OpenCode | The open source AI coding agent

OpenCode - The open source coding agent.

@Xavier @plexus There's also "aider" which is also a CLI tool for LLM-assisted programming: https://github.com/aider-ai/aider

Though my experiments with it and local models are pretty... meh. I was trying it with a quantized Llama 3 derivative and the code it wrote was mostly a mess. It was okay at *drafting* documentation from existing undocumented code, which is decently useful at times.

In 5+ years I could imagine they might have a local model that would run well enough to use it as a really overgrown shell, though.

GitHub - Aider-AI/aider: aider is AI pair programming in your terminal

aider is AI pair programming in your terminal. Contribute to Aider-AI/aider development by creating an account on GitHub.

GitHub
@Kadin2048 @plexus I'm coming to the same conclusion. I'm not happy with the output of local LLM coding assistants just yet. Ollama is great as a replacement for AI agents that need to make API calls, but I'm not seeing the level of reasoning that makes Claude Code so effective. We're close, but not quite there.
@Xavier @plexus Yeah, I think some of the Llama 3 derivative models, run locally through Ollama, are good enough to use as a sort of giant natural-language shell. You can have it commit-this, reorganize that, etc.; seems excessive now but when you can run it locally on a phone in a few years, it'll be a hell of a thing.