HN user
Something very small and simple compared to other ambitious projects here :)
A TUI to control a crazyflie nano drone. This is mostly a rust learning project - but insanely fun because it leads to something flying through my living room.
Even their sales teams work with GitHub repos, so not that surprising I’d say.
Those are often also people who are in the company for a long time already, not only newly hired. I think AI makes it just so easy to be lazy.
I guess my hope with the face to face is that people take the feedback and learn to do the actual work again. Right now it feels like a lot of this kind of collaboration and what is okay and what no has to be figured out.
That is something I actually have not noticed, do you get pushback like this?
I mean I agree with you, but the reality for many of us is that this is not under our control?
As everyone is an expert now[1] on paper I think it is unfortunately time for a shift again. For years I was big proponent of asynchronous remote work. But it seems like the only reasonable way forward is to discuss things face to face. I still prefer to prepare things async, but then discuss them in person to understand if people actually understand what they are talking about. So far I also have a good time with really being frank and honest with colleagues if something is clearly AI expertise and not that persons expertise.
Mostly though if you do anything with the returned value at the call site you need to change that code anyways? If it is not just passing it on, and even then you might need to adapt its signatures. E.g. if you change from String | Null to String you remove the null handling. If you add Null you need to add Null handling?
Thanks for sharing.
But you will end up with something where you can say „this is mine, I did that“ for the rest of your life. Even if no one ever cares. I come back to some of the things I did in the past through hard labour (coding projects, skateboarding videos) and even if it is nice if others appreciate this, they are still always there for myself as sign of what I achieved.
How will fake stars help it getting of the ground?
I guess the idea is to show a small token of appreciation. I do that and I am also happy if I receive some on my own repos.
I felt exactly the same, but recently started building side projects again in Haskell and fell in love again. Really brought my passion for software development back. 2026 feels perfect for that, as AI can help with things where one was stuck, not the stuck in a good learning way, forever in the past. Now is the time!
Same here it just feels like something so simple, I’d rather have it under my own control. That way I can keep it independent of claude as well. I use it for all kind of routine tasks like updating the summary of projects I am working on or tracking some personal activities. My setup looks like this: https://www.dev-log.me/click_recurring_tasks_for_claude/
That sounds awesome! I basically do all the same sports, but I always need to win or to get better at them. I am trying to move in your direction though.
Awesome, I am finding so little actual experience reports on this, if you build something similar, I'd be very happy to hear about how it's going. Feel free to reach out directly to me.
Thank you for sharing that. I am going to save this one. Does that work for you? Could you shift from winning at things to just doing them?
While working on a sideproject I explored lean 4 a bit and figured it actually something that can be very easily integrated into any project if one wants to prove correctness.
Nice thank you. If something came out of this that would be amazing. I am not the biggest fan of mcp, as they are a waste of tokens though. I shot you a message on LinkedIn as well, was wondering if this caused some discussion internally at Rewe because it was immediately blocked.
Yes and I do. My above point was just that I’d like to have fast inline auto complete.
I tried copilot for a bit in vscode as well with opus and felt something was off. Somehow as if copilots harness around it just wasn’t as good. But I can’t give solid prove.
It took hours not weeks. You were absolutely right.
In the authors enter first and last name example, isn’t the do notation also much clearer on order of effects? Eg being asked first for first name?
I just wish Claude code would also offer fast inline auto complete. Sometimes I’ll just want to have a function definition or some boilerplate spelled out without waiting for the slow Claude response. Or actively switching models. ——- Maybe I can set up a shortcut for that?
there is this "400g (1 kg = 3,48 €)" - would be pretty easy to sort results by that I'd guess, good idea!
It is extremely simple. I just tell Claude: "Use korb to look at my order history and create a table with my most frequently bought items. Next time, fill my basket with the items I always buy." So something of that variation works.
Thank you. Though I have to say I'm really not an expert in that domain and just starting to explore it myself.
You can already filter by `isRegional`. That's maybe close enough.
This is also my exact workflow here. Thank you. I'm adding things that should be in the basket via Siri to my Obsidian notes. I also add recipes to that list or anything else. Then Claude checks that list once I want to do the shopping, looks through my favorites, and fills the baskets with all the items needed. I also use Claude to list the most frequently bought items for a template that always gets filled in.
I mean, definitely leads to me buying more stuff on Rewe than before.
I mean, fixing small issues is not a big deal – during my ordering sessions, if something comes up, I actually just let Claude create an issue for it, and then when I have time, I create a fix.