I guess that depends on what you define productivity as. It seems that you have a preconceived narrow definition. If I pay millions of dollars in taxes that fund a war, who is to say that was more productive than planting a tree and taking a nap.
If you re-read my comment, you will notice that I said nothing about how much taxes are paid, or what those tax dollars are used for. I was talking about how much time, energy, and capital is needed just to figure out how much you owe.
It’s using AISDK and MCP-UI, which is standard for chats. If you check the cart in the input, there’s only 2 stores added for now.
Also, that chat is just one part of it. Those stores are running on Openfront, our Shopify alternative. Please check our ethos to get the full vision.
Also, I was working on this before AI. Openfront and the/marketplace are part of an ecosystem. We built Openship, an e-commerce order management system, years ago.
Don’t confuse vibe coding with a low effort build, vibe coding can lead to the high-quality, amazing products. I’m just here to protect the vibe coding phenomenon :D
It's just a semantic disagreement. In my experience, "vibe coding" means "software made with genAI, casually iterated until it passes tests and appears to work, without exhaustive or experienced review of the output, and is therefore often bad." It doesn't have to mean that, but in practice that seems to be the dominant definition currently.
I watched YouTube howtos, and read 1000 stackoverflow results around 2016 and made my own saas for the construction industry in PHP/jQuery. Was a car salesman before that.
I have 34 companies using it today.
I promise you, a vibe coded app would be an improvement.
So what's the problem really?
10 minutes after your comment I checked and I don’t see any pgsql credentials, but I do see that they have committed their local settings instead, including their local file paths now.
The API is a way to access a model, he is criticizing the model not the access the method (at least until the last sentence where he incorrectly implied you can only script a local model, but I don’t think thats a silver bullet, in my experience that is even more challenging than starting with a working agent)
This commit graph seemingly shows that they fixed a couple bugs over like a week. Period that involves changing like six lines of code. That code has no abstractions no structure and several problems you could poke holes in. While it may work and that’s great for whoever benefits, this isn’t very convincing as I can currently write more than six lines of code per day by hand
I am not an electrician, but when I did projects, I did a lot of research before deciding to hire someone and then I was extremely confused when everyone was proposing doing it slightly differently.
A lot of them proposed ways that seem to violate the code, like running flex tubing beyond the allowed length or amount of turns.
Another example would be people not accounting for needing fireproof covers if they’re installing recessed, lighting in between dwelling in certain cities…
Heck, most people don’t actually even get the permit. They just do the unpermitted work.
To add onto this, it is a characteristic of their design to statistically pick things that would be bad choices, because humans do too. It’s not more reliable than just taking a random person off the street of SF and giving them instructions on what to copy paste without any context. They might also change unrelated things or get sidetracked when they encounter friction. My point is that when you try to compensate by prompting repeatedly, you are just adding more chances for entropy to leak in — so I am agreeing with you.
> To add onto this, it is a characteristic of their design to statistically pick things that would be bad choices, because humans do too.
Spot on. If we look at, historically, "AI" (pre-LLM) the data sets were much more curated, cleaned and labeled. Look at CV, for example. Computer Vision is a prime example of how AI can easily go off the rails with respect to 1) garbage input data 2) biased input data. LLMs have these two as inputs in spades and in vast quantities. Has everyone forgotten about Google's classification of African American people in images [0]? Or, more hilariously - the fix [1]? Most people I talk to who are using LLMs think that the data being strung into these models has been fine tuned, hand picked, etc. In some cases for small models that were explicitly curated, sure. But in the context (no pun) of all the popular frontier models: no way in hell.
The one thing I'm really surprised nobody is talking about is the system prompt. Not in the manner of jailbreaking it or even extracting it. But I can't imagine that these system prompts aren't collecting mass tech debt at this point. I'm sure there's band aid after band aid of simple fixes to nudge the model in ever so different directions based on things that are, ultimately, out of the control of such a large culmination of random data. I can't wait to see how these long term issues crop and and duct taped for the quick fixes these tech behemoths are becoming known for.
Talking about the debt of a system prompt feels really weird. A system prompt tied to an LLM is the equivalent of crafting a new model in the pre-LLM era. You measure their success using various quality metrics. And you improve the system prompt progressively to raise these metrics. So it feels like bandaid but that's actually how it's supposed to work and totally equivalent to "fixing" a machine learning model by improving the dataset.
reply