So many things - reminds me of the days when you'd throw together a quick shell or Perl script to solve a very particular itch. So I have a whole collection of apps, portals, demos, etc.
Which is what leads to my issue: cognitive overload, and very high context switching costs especially as I'm usually on multiple work and "hobby" projects at a time, with multiple projects spread across term tabs, IDEs and Claude remote on phone.
So I built a "Workshop" to tinker. It analyses all the projects I'm working on currently as git repos on disk, then builds project pages complete with summary and a full control and data planes including its own startup method, commits being made etc. It does some agent introspection so it's able to display all agents running on machine in unified view.
But the "killer" feature for me is the "Pulse" - this contains human readable summary of what's happening with each project and agent in real time. So one use case is an "overnight view" - I set up architecture and design, assign the agent a goal, then wake up next morning to quickly scroll through the results. It also lets you track changes happening in real time ("We finished adding an export function for receipts, containing your company logo and signature" to summarize a feature across 10 commits).
I also added other useful to me utils such as being able to append a ? To any command in its inbuilt terminal and it'll convert it from English to a cli command waiting for you to confirm, for example; a system load monitor; a network sniffer, sys admin tools etc. all written in Rust, which I've never written a line of :)
Will put it online but need to clean it up first it's very specific to my use cases so not sure it'll be useful to others.
“Kills the fun part of coding” - absolutely not! Coding is a lot more fun now that I can move from idea to working prototype in an evening without having to figure out individual libraries, research and learn them etc. The last time I felt this excited / into tech was when I first discovered Ruby on Rails and started using it for projects.
I’ve done several projects that would take months to complete otherwise with “vibes coding”, including: an African fairy tale generator for my daughter, a farm management system for the ministry of agriculture in my country, a Gambian political comic strip creator, a system that generates ten minutes summary podcasts of all my country’s news etc. I’ve also had great success with clients - and got them to sign on much faster - by just putting together a quick demo now that I show them instead of sending a proposal and pitch deck describing what I’ll build for them. It makes them so much more excited and we can make changes almost in realtime.
I’ve noticed a lot in the industry and even on hn, that coders - especially long time ones - tend to “look down” on vibes coding, the same way they did with scripted languages back in the day, and I imagine the same way with compilers. I think this will generally fade out as it becomes industry standard, but in the meantime sometimes I see comments on hn that are so discouraging and cynical it makes me wonder if the person actually tried it out or had just pre judged it. I also think the phrase “vibe coding” is a terrible name, cause it makes it sound like a lazy way of doing things. It’s so much more than that, and lets you think and plan at the idea level. Things like planning your system before you ask it to implement also help a lot.
I think he missed one of the use cases for advertising: providing “free” services to people in the “third world”. I come from west Africa, majority of people can’t afford to pay for Facebook, YouTube, whatsapp etc even though these are their main means of communications. Even if they could afford it (“just a few cents is nothing” to us on here - to these people that’s how much they make in a day), they don’t use traditional banking services and certainly not access to credit and debit cards to make payments. I hate ads too, for all the reasons mentioned in the article. But I don’t see a feasible way to make these services available for the 1 billion plus people I’m describing. Open to ideas.
Not yet as I’m still finessing it to her needs. She has a problem getting rid of thumb sucking, and finally asked for a fairy tale with a thumb sucking princess who eventually stops sucking her thumb lol. It’s a fun activity and also letting me learn about LLMs.
Will do. Hn has no way of tagging people or following up though so I’m not sure how to share once I go live. But if you shoot me a message I’ll update you once done. amrangaye at gmail dot com.
Thank you. Yes she’s been enjoying them a lot now that we don’t have to repeat the same stories every night :) I’ll share on here once I’m done and also the right up.
Does “vibe coding” count :-) I’m from west Africa and lately been very interested in African fairy tales to read to my daughter. Ended up building (
a GPT-backed interface that can insert her in any African story she wants. We also have a list of African queens who’re not famous anymore but did amazing things (look up Queen Nzinga for example). So I’m doing a series of little children’s books about each queen - have them exported to PDF so I can print them out and bind for her: her own little
Collection of fairytales. I plan to put it online later - even if you’re not African I think it’s a great way to explore our history.
+1. And “figure out a government ledger” sounds like a friend who would ask why google spend so much money when “it’s just one page with a search box”. Government spending and the amounts involved in budgeting and appropriation etc are far more complex than that, even for small countries.
“The majority of them don’t even have taste” - by your definition of taste perhaps? :-) just sounds condescending - taste is whatever they like, not what you decide is good to like.
Only a “laughable debate” and “just the free market” if you haven’t actually had to deal with these insurance companies when you have a health issue and have never paid your dues late. I’m guessing you’re from somewhere in Europe with universal health care?
Sidebar: interesting how you typed out the email address (I’ve also seen variations like me at gmail dot com). This worked for spam and phishing crawlers that just did a brute force search across texts. But now that we have LLMs, I’m wondering if this will be effective anymore, since it gets the context as well and is not just a “dumb” regexp search?
I’m heavily invested in 1p for years now, but have been impressed by the new Apple Passwords app (in beta) - it’s nowhere near as advanced, but it implements like 90% of what you need including 2FA. I’m sticking with 1p for now but worth watching as well.
lol - just out of curiosity: are you doing this yourself? Provide tech support to all your aunties and uncles, cousins, friends etc (already bad enough - now formalized) then you add installation and maintenance (including on all their devices), keeping everything updated etc. And having to troubleshoot every single problem they run into.
“make decisions as a group” sounds great and democratic - but you really think anyone cares about this enough amongst non-techies to be part of all this “decision making” about what apps to use? And this is in addition to your day job. And please don’t say well we can evangelize - again: no one has time for that.
It sounds great esp to us techies - that’s how WE would solve the problem as a group. Doing that with non-techies esp with family and friends would be HORRIBLE in practice. Unfortunately I have a feeling I’ll get responses of the type “well you never know till you try” and “maybe YOU can’t / don’t want to do it but others will”. To which I say more power to you :) but this is def not a solution outside of hacker forums where we can pore over tech surveillance and freedom etc. and create a bubble where everything is libertarian and can be solved if only we had the right systems in place for the normies.
I thought it was just me - I even tried different mobile browsers. You’d think before you wrote a whole article about how bad Wikipedia is you’d at least make your site work on mobile. (And I have js turned on - the site is just one long column of unreadable text)
> Kinda. We were open to believing in God. But the start of our journey was just realizing the secular world had nothing to offer us.
I'm curious how you interprete "secular"? Cause it seems you're setting it up to mean anti-religion which is certainly not what the usual definition is.
> Here’s the thing: if you’re not a militant atheist and you start spending a lot of time around sincerely religious people who you like, you’ll end up believing sincerely yourself.
I won't question your own experience, but you're being way too broad here. I know many people who are not "militant atheists" but still don't believe in organized religion. I also have a lot of friends whose families are extremely religious - meaning they're around them all the time - none of them has been pushed or convinced to join. They just don't observe prayer etc compared to their friends.
> Since you’re secular, I’ll explain it like this: we’re evolved to cohere around a shared system of belief and the appropriate mental machinery will kick in as part of becoming embedded in a religious community. And that’s what I used to believe. But now I know those were just the breadcrumbs I needed to find my way.
This sounds more like a self-justification than something actually supported by science. Please note I'm not trying to "religion shame you". Just curious. :)
Which is what leads to my issue: cognitive overload, and very high context switching costs especially as I'm usually on multiple work and "hobby" projects at a time, with multiple projects spread across term tabs, IDEs and Claude remote on phone.
So I built a "Workshop" to tinker. It analyses all the projects I'm working on currently as git repos on disk, then builds project pages complete with summary and a full control and data planes including its own startup method, commits being made etc. It does some agent introspection so it's able to display all agents running on machine in unified view.
But the "killer" feature for me is the "Pulse" - this contains human readable summary of what's happening with each project and agent in real time. So one use case is an "overnight view" - I set up architecture and design, assign the agent a goal, then wake up next morning to quickly scroll through the results. It also lets you track changes happening in real time ("We finished adding an export function for receipts, containing your company logo and signature" to summarize a feature across 10 commits).
I also added other useful to me utils such as being able to append a ? To any command in its inbuilt terminal and it'll convert it from English to a cli command waiting for you to confirm, for example; a system load monitor; a network sniffer, sys admin tools etc. all written in Rust, which I've never written a line of :)
Will put it online but need to clean it up first it's very specific to my use cases so not sure it'll be useful to others.