The irony is, that by drawing attention to these, especially on HN, they are likely to have the view numbers artificially increased, to a point where they no longer has_not_been_viewed_much
In the old days (a few weeks ago) you could read google’s SEO recommendations and guidelines.
This was great for debunking many a recommendation from clueless SEO agencies trying to force requirements on dev teams.
Is there any similar recommendations available for their new, LLM, world?
Why do many people seem to think we have solved human robots because of the advances in LLMs? We are still yet to solve 4 wheeled robots navigating a constrained environment. Are we really expecting these things to be let loose _in people’s homes_?!
Also, while we're on the topic, if you ever find your self at the other end of the world in Tasmania, I highly recommend a visit to the MONA museum, which houses the Poo Machine.
This _all_ (waves hands around) sounds like alot of work and expense for something that is meant to make programming easier and cheaper.
Writing _all_ (waves hands around various llm wrapper git repos) these frameworks and harnesses, built on top of ever changing models sure doesn't feel sensible.
I don't know what the best way of using these things is, but from my personal experience, the defaults get me a looong way. Letting these things churn away overnight, burning money in the process, with no human oversight seems like something we'll collectively look back at in a few years and laugh about, like using PHP!
Nah man. I understand the frustration, but this is a glass is half empty view.
You have decades of expert knowledge, which you can use to drive the LLMs in an expert way. Thats where the value is. The industry or narrative might not have figured that out yet, but its inevitable.
Garbage in, garbage out still very much applies in this new world.
And just to add, the key metric to good software hasn't changed, and won't change. It's not even about writing the code, the language, the style, the clever tricks. What really matters is how well does the code performs 1 month after it goes live, 6 months, 5 years. This game is a long game. And not just how well does the computer run the code, but how well can the humans work with the code.
Use your experience to generate the value from the LLMs, cuase they aren't going to generate anything by themselves.
This is a great and worthwhile discussion. People are loosing sight of what art is. The art is the idea, not the medium. And just because something is easy, doesn't mean it will be good.
I've seen some fantastic original pictures that actual artists have generated through AI. I can't wait to see what current and future artists can do with the new tools at their disposal.
I don't understand the fascination and focus on Vibe Coding.
Sure, you can do that, it's an option, but no serious engineering effort is being left entirely up to the AI.
Vibe coding is essentially the Jackson Pollock approach to software building. Throw a bunch of paint down, with very little control, and look, we have something novel.
It doesn't mean your going to replace all the ways of making art with paint throwing.
I'd love to start seeing more discussions about alternative approaches to working with AI. The recent Vinext article was great https://blog.cloudflare.com/vinext/. This seems to be "the way" for working with AI in a high stakes production environment, but what other ways are there.
I fear the focus on vibe coding is diluting and taking focus away from far better alternatives. Maybe because the narrative around those aren't quite so dramatic?
Thanks for the reply Jeff. This aligns with my understanding too. I'm close to purchasing a mac mini to replace my aging media pc. The core feature I want is to run microK8s natively, which I'm assuming the newish Mac containers will support.
Thanks for the reply. I'm looking to replace my aging mini pc with a mac mini, so I'm quite interested in any limitations here.
The full disk encryption I can live without. I'm assuming these limitations don't apply if it's disabled. [Ah, I just saw the other reply that this has now been fixed]
I was aware of the Docker in a VM issue. I haven't tested this out yet, but my expectation is this can be mitigated via https://github.com/apple/container ?
May I ask, what experiences are you personally having with LLMs right now that is leading you to the conclusion that they will become "intelligent" enough to identify, organise, and build advancing improvements to themselves, without any human interaction in the near future (1 - 2 years lets say)?
Is it just me, or does there appear to be a big gap in how people understand this works?
There is no magic here. Replace "car" with some nonsense word the LLM hasn't encountered before. It will completely ignore the small amount of nonsense you have provided, and confidently tell you to walk, while assuming you are talking about a car. I'm fairly confident the first time this was tried using "car", it told them to walk.
"I want to wash my flobbergammer. The flobbergammer wash place is only 50 meters away. should I drive or walk."
Reply:
If it’s only *50 meters away*, definitely *walk*.
That’s about a 30–45 second walk for most people. Driving would likely:
* Take longer (getting in, starting the car, parking)
* Waste fuel
* Add unnecessary wear to your car
* Be objectively funny in a “why did I do this” kind of way
The only reasons to drive would be:
* The flobbergammer is extremely heavy
* Severe weather
* You have mobility limitations
Otherwise, enjoy the short stroll. Your future self will approve.
Via chatGPT free tier. Paid Claude Sonnet 4.5 Extended gives me:
For just 50 meters, you should definitely walk!
That's an incredibly short distance - less than a minute on foot. By the time you'd get in your car, start it, drive, and park, you could have already walked there and back. Plus, you'd avoid the hassle of finding parking for such a short trip.
Walking is easier, faster, better for the environment, and you'll get a bit of movement in. Save the car for longer distances!
I'm missing the point? I literally asked the same thing you did.
>Now what....? Whats happening right now that should make me care that AGI is here (or not).
Do you have any insight into what those changes might concretely be? Or are you just trying to instil fear in people who lack critical thinking skills?
A new field is required…