Remix.run Logo
dingnuts 7 hours ago

> The gap between engineers using the tools and those not are continuing to grow

Yeah, the ONLY place I hear this where it means "AI pushers are getting faster" is on this website, where half of your salaries depend on said belief.

When I go outside and talk to real engineers who I respect, in confidence and away from the suits forcing them to use AI, away from the hype of the industry telling them only one opinion is allowed, they all agree that "agentic coding" is simply not a meaningful improvement in quality or speed of publishing working software in the real world.

Maybe you like it, and that's fine. If you want to pay a lot of money for advanced IntelliSense and you can get your boss to do that for you, have fun. Just don't force it on me.

I don't believe you'll be meaningfully faster or produce better work than I can without the clanker's help.

If I get furloughed I'm going to get a new career working with my hands.

skydhash 6 hours ago | parent [-]

I’m still waiting for an article like this one:

https://jlouisramblings.blogspot.com/2013/04/acme-as-editor_...

It’s clear, informative, and even without reproducing it, you can still form an opinion about the tool.

All the AI pushers’s comments are either very vague or experiments whose sole quality is that it has been done with LLMs (often badly).

ares623 3 hours ago | parent [-]

There’s been a few that show the Git history of a project that were (allegedly) fully written with an LLM. Not fully vibe coded, but in a meaningful amount.