Seeing a lot of these “run 1TB models with 1GB RAM” projects recently. Most seem vibe coded and probably won’t be maintained.

Hoping a winner emerges with some real momentum behind it.

▲

mkagenius 22 minutes ago | parent | next [-]

I love how goal posts are shifting from "vibe coded apps dont really work" to "vide coded projects wont be maintained"

▲

hiramwen 7 hours ago | parent | prev | next [-]

You don't really need a maintainer when codex or claude code can set it up for you; thats how I got Trellis2 working on windows and tiny VRAM despite Microsoft recommending you have 24GB VRAM and Linux. Models are pretty disposable now.

▲

tecleandor 5 hours ago | parent | next [-]

So, instead of having one or two maintained projects that work super well, now we have hundreds or thousands of people half-assing it locally each time they need it? Doesn't sound efficient.

	▲	IAmGraydon 3 hours ago \| parent \| next [-]
		It might make sense to do this if there literally isn't an existing solution out there, but I think most would find that it's better to use an existing solution than to recreate the wheel every time there's a need. It's just less effort/time/money.
	▲	esafak 4 hours ago \| parent \| prev [-]
		I have the same objection to forking open source projects; changes should be upstreamed when possible.

▲

titularcomment 6 hours ago | parent | prev [-]

This is complete dependency on LLM tools all the way from development to usage, and is risky as well as prone to failure

	▲	hiramwen 6 hours ago \| parent [-]
		Local inference without access to internet and tools is pretty safe, worst you get is a slop output, best case it solves your prompt.

▲

akie 7 hours ago | parent | prev | next [-]

No no, don't just say "vibe coded", say "Fable and $500 of credits"

▲

ricardobayes an hour ago | parent | next [-]

Or Deepseek with a fiver.

▲

Foobar8568 6 hours ago | parent | prev | next [-]

Opus 4.6 was already enough to tackle these projects vibe coding.

▲

gwerbin 5 hours ago | parent [-]

Incidentally I think I was more productive with Opus 4.6 than with any subsequent Anthropic model.

	▲	cute_boi an hour ago \| parent [-]
		Yea, opus 4.6 is much better than opus 5 because it is willing to do task. Opus 5 just gaslights and refuses to solve many complex problem.

▲

cyanydeez 2 hours ago | parent | prev | next [-]

these things can be done with local models; so don't say 500$ credits, say "accelerated climate change disasters by $500/year"

▲

Lalabadie 7 hours ago | parent | prev [-]

"This one is made with premium vibes"

▲

classified 7 hours ago | parent | prev [-]

How a patchwork of Python modules constitutes an API(?) or whatever(?) and how to use it (does anyone?), is beyond me. There is nothing that I would call documentation, let alone concrete usage examples. I know more amusing ways to waste my time. When I want to play with models, I use llama.cpp.