> If you weren't able to build it before then you aren't able to properly verify it
GP said "couldn't dream of building". To make an analogy, I wouldn't dream of building a house if I had to do every bit of brick-laying myself. But with others doing what I can't do, I can indeed dream of building a house and I do know how to verify that the house was built to satisfy my dream.
It could just be that each of the two reviewers is merely focussing on different sides of the same coin? I use Claude all the time. It saves me a lot of effort that I would have otherwise spent in looking up specific components. The magically autocompleted pieces of boilerplate are a tangible relief. It also catches issues that I missed. But when it is wrong, it can be subtly or embarassingly or spectacularly wrong depending on the situation.
> I can still run 2-3 clients almost 24/7 pumping out features.
Honest question. How does one do that? My workflow is to create one git worktree per feature and start one session per worktree. And then I spent two hours in a worktree talking to Opus and reviewing what it is doing.
I am hearing this term for the first time but I love it. It is novel and creates a picture. Exactly what Scott Adams says about labels used for persuasion. I usually say "highly trained autocomplete" in discussions at work, but I am going to say "stochastic parrot" from now on.
> everyone that claims it makes them so perceptively and clearly faster - how do you know?
For me, AI tools act like supercharged code search and auto complete. I have been able to make changes in complex components that I have rarely worked on. It saved me a week of effort to find the exact API calls that will do what I needed. The AI tool wrote the code and I only had to act as a reviewer. Of course I am familiar with the entire project and I knew the shape of the code to expect. But it saved me from digging out the exact details.
Everyone seems to be missing the point. Using an LLM to perform book keeping like this is akin to a business in the dot-com era hiring a programmer to help them go online. But since it's an LLM, the next step would be different. The LLM might initially do all the actions itself, but eventually it should train optimised pathways just for this purpose. It would become an app that isn't actually written out in code. Or alternatively, the LLM might actually dump its optimized logic into a program that it runs as a tool.
I am amazed by your negativity at comments written to support all the gushing praise. It's really cool to support cool things and even though those comments are not perfect we should appreciate the effort that people put into making HN a more positive space.
I am in that trap myself. I am doing work that I like, at a pay that I like but "something" has been missing for a long time. Two decades ago, back in my grad school days, I used to have a blog and was part of communities like livejournal. Now my blog is replaced with a blank page because I have nothing to share with my friends about my daily life.
Come on, it can't be that bad! If such small nerdy groups existed, what are the chances that their membership does not overlap with places like HN? It would only be a matter of time before we heard about them.
> I am now older and more burned out and less prone to chasing after cool new things.
Yeah, mostly true for me too. I hear about cool new things, but rarely choose to chase after them.
I am not entirely sure that this is a bad thing. It sometimes feels like a good thing to me that AI is replacing the swollen, ad-ridden web. Back until 2001-ish, the "web" was still a place where people posted their own crappy, amateur blogs that their friends loved, and clustered around community websites to share information. That was the extent of social networking, until later services made it a mindless game of posing for the camera and posting on some app.
Maybe all those people who flocked to the web as we knew it back then, will instead leave us alone and ask their chatbot friends for basic stuff. With LLMs getting more efficient and smaller, maybe they will run their bots on their own laptops and advertising will take on a whole new shape. Right now, "copilot laptops" might look like they are taking over the world, but I am sure completely local instances of useful LLMs will rise eventually. Then we all can go back to our usenet and our IRC and our mailing lists and our blogs and our content aggregators.
And no, not sarcasm.
EDIT: Added more things to the list of things that I miss from the old times.
I didn't mention any particular sense about application inside an application. I did say how it "feels like to me" and how my brain fails to handle it. There is a clear shift of modes when I click on a link on a website and suddenly the contents of the current browser window are replaced by a pdf with its own back and forward buttons, its own page layout, its own toolbar and so on. If it stopped feeling different like that, I would not even notice it and wouldn't even bother to find out if what I am seeing is a pdf or an html based website.
Opening a pdf inside a browser feels to me like an application inside an application. My brain can't handle that load. I would rather have the browser to browse the internet and a pdf reader to display pdfs. If I clicked on a link to a pdf, it is _not_ part of the web, and I want the browser to stay out of it. Same goes for Office 360 wanting to documents inside my browser. I don't want it to do that. I have the necessary apps installed for it.
> However I'd like to dig a bit deeper into the real value of this for a user of "stays with Emacs only Magit"-type.
That right there is the problem. I have been an Emacs user for decades. Magit is awesome because of Emacs, not inspite of Emacs. Whatever this person is saying, either they have not given any real thought to their own experience, or they really don't care about anything other than Magit as a piece of software that they prefer using. If it's the latter, then only that person can tell you what is so great about Magit. But that line of thought is really hard to understand and counter for a typical developer who cares about their entire coding experience and not just any one package.
> However, all those Doom users evaluating to move to "mainstream" editors, who do only minor adjustments (like options, keybindings), do they get something substantial from Magit that they can't achieve in those editors?
No. I would be very skeptical of people who make such claims.
I have tried explaining magit to my fellow developers. And they kept showing me how they do similar things in their favourite IDE. Turns out that Magit in itself is not compelling. You have to first appreciate Emacs, and then you notice how perfectly well Magit "raises" git to the Emacs abstractions. I love Magit and rarely use the git commandline. But that's because Emacs fits my brain perfectly; the way Emacs deals with "things" (pun intended) is exactly how my brain works. And then Magit just makes version control feel like Emacs front and center.
GP said "couldn't dream of building". To make an analogy, I wouldn't dream of building a house if I had to do every bit of brick-laying myself. But with others doing what I can't do, I can indeed dream of building a house and I do know how to verify that the house was built to satisfy my dream.