[twoquestions]

People keep comparing LLMs to automated looms, but I find them more comparable to cruise control than autopilot.

I've been working on a character sheet application for a while, and decided to vibe-code it with Spec-kit to help me write up a specification, and for things I know it's been great. I tried using Claude to make it into a PWA (something I don't know very well) as an experiment, and I've found the nanosecond the model strays out of my experience and knowledge everything goes straight to Hell. It wraps my codebase around a tree as if I'm not paying attention while driving.

It's a tool you'll have to learn to use, but I can say with absolute confidence it's no replacement for actual skills, if anything it highlights the gulf between people who know what they're doing and people who don't, for better and worse. It sacrifices some of the 'code under your fingers' feeling for management tasks, which I personally really like, as I've always wanted to document/test/code review/spec things out better, and I now understand the pain of people who'd rather not do that sort of thing.

https://github.com/github/spec-kit

[pron]

The difference is that you can trust cruise control to do whatever limited job it knows how to do; you can't trust an LLM to do anything. That makes it, I think, hard to compare to anything we're used to (happily) working with.

[hansmayer]

Cruise control is a useful technology, that once you learn to use, it's automatic (somethingsomething pun something). LLMs on the other hand - well, yeah - if you like playing chess with pieces and board made out of smoke (to paraphrase Jerry Seinfeld), sure you'll probably figure it out...some day...

[melagonster]

I do not know... I keep seeing everywhere, people promising that agent-based tools can solve all these problems and handle full, project-level tasks.

[boringg]

Those same people have large equity stakes or are in the surrounding network companies dependent on AI being successful.