Super cool writeup from a technology perspective. And a motivator to build more tools, play with MCP and try out Claude routines. The product pitch is also really clear. Good job all around.
Now for the criticism:
back in the day mint.com was mind-blowing. It's what you always thought you'd wanted. The graphs were interactive and pretty and you really loved seeing them go up. Not so much down. I was so attached to the gamified aspects, much like step counters. They reinforce habits.
My mint journey ended with roughly 5 years or so of data, once they sold to Intuit, didn't like the ads and willingly syncing all my data to mega-corp. Much like Duolingo, it felt good at the time, but I don't know that it did anything for me at all.
Tracking is a double-edged sword: it really does build better habits. It's better to track weight every day for example so you better understand that fluctuations are mostly noise. The daily tracking stuff is entirely useful to get the need to track daily out of your system.
TLDR: checking my net-worth daily sounds like something I should coach myself out from. Ironically that probably takes tools, but the end goal is to not need them.
Awesome feedback. Agree 100% with this. I guess a couple comments:
- We have a built-in CSV export tool in beta right now for cash transactions, and plan to add this for other datasets as well. You should be able to download your data when you want it. It's yours.
- Yes, tracking is great, but it also has a dark side. My sort of vision, at least for what I want, is less of a gamified finance tracker and more of an ambient, always-on agent that's watching for me. It knows my preferences, it knows what I care about, and it tells me when it finds something.
- Before we get there though, for now, it's really interesting to sort of tinker and build your own custom finance automations. As a programmer, it just feels liberating to get the data out of some closed banking app and into a space I'm comfortable in.
- Especially from an investing standpoint, it's been neat to pair our MCP with a much smarter model like 5.4 Pro and have it do long-horizon research tasks that require a lot of web research and correlation.
> As a programmer, it just feels liberating to get the data out of some closed banking app and into a space I'm comfortable in.
Quote of the week for me. well said.
~15 years ago I fumbled around with web programming basically because I never learned how to use excel in school. Nerded out with css, html, forms, then php and mysql to script together an unbelievably worse version of what a spreadsheet could do, but it was incredible that I could build something entirely made for my idea. And with the power to improve it.
Thank you for writing and sharing your story, it's motivating and comforting even. Good luck!
I didn't want to even try it because of similar. ("immigrant mentality" they call it around here. it's not a pejorative. TLDR: frugal because starting life over)
and it's really slow. I didn't end up waiting. Not a slight to the creators, let them create. It's just really freaking slow I didn't wait.
same. i finally tried Claude Code and i just shrugged. Cursor definitely has a clunky UI with an identity crisis, but it pioneered plan mode, and auto / composer chugs along without rate limits for the most part.
I don’t doubt it is. End of the day, it’s a fine tuned Kimi. They tried to hide it and making their work sound more impressive than it is. It’s easy to have stuff be cheap when you don’t have to train your own model from scratch.
You might be onto something. I find every image unsettling. they're very good no doubt, but maybe it disturbs me because all of it is a complete copy of what someone else created. I know, I know, there is no pure invention. That's not what i mean. Humans borrow from other humans all the time. There's a humanity in that! A machine fully repurposing a human contribution as some kind of new creation, iono i'm old, it's weird and i don't like it.
Downvotes because nobody actually wants this. Those image uses serve a purpose to an external audience. The audience doesn't want this shit.
Now of course I'm being dramatically absolute. I'm sure I already consume these things without knowing it. These things serve a function. Offloading to AI is the implementer admitting they can't be bothered to care whether it serves the function.
Agree with the problem but this list reads like a vent.
Communicating effectively is the central problem of all humanity!
This vent criticizes developers for not knowing how to listen. that's why it comes off condescending. The root problem is that people don't know what they don't know.
The best communicators are translators. People listen because the message becomes self evident in their understanding.
It's hardly a breakdown because everyone is acting like a toddler with their fingers in their ears.
This is ironically why we reach for systems and engineering. The system can build in gap detection and frameworks for translation. It's not perfect and creates its own problems but scolding each unit human to listen better does nothing for the collective environment: the team, the company… the system.
Passing on what an ancient greybread told me. He said look at it as a Noisy system (signal is always lower than noise no matter what you do) with bounded chimps inside it.
Bounded meaning there are upper limits to what anyone can do. And there are upper limits to how frequently model updates of the chimp brain can happen per unit time. And the limits of a group are much lower. At the extreme end Large institutions once they settle on a model of reality can take decades to radically update it. Even if all signs say reality has totally changed.
So with those constraints in mind decide what you want to spend your energy and time on.
Sounds like innovator's dilemma + a quote i saw recently:
Former UK Prime Minister Margaret Thatcher: “Consensus ... is the process of avoiding the very issues that have to be solved.”
I buy that inevitably the system becomes it's own constraint and local optimum. But working together is a practical reality too. Worth making the best of.
I am a developer, I also have worked enough other jobs to know how important communication is and how bad developers can be at it.
A typical pattern I recognized is that many developers communicate like bad medical doctors: they do "Mhh, Ahh" and then after a way to short period they fire out a diagnosis of what you need, sometimes without you even having said everything relevant yet.
It is nothing new that people in software are at times not the best communicators. For the first part the interesting bit isn't what your clients want, it is what they need. Unless they are the usually rare customer that has a good understanding of how software could solve their problem elegantly, you will have to assume it was someone's job to come up with something and that someone has never written or thought a lot about software before. That doesn't mean their ideas are worthless, but it means the work of finding the requirements and coming up with a solution is usually not done when you arrive. And the way to get it done is communication, by observation and by having them explain the processes.
Many software developers are in fact really not listening in my experience. Not that developers are the only people that happens to, doctors or other technicians also come to mind. They are often trying to quickly come across as competent by showing off their good grasp of the subject. To them you are a clear case of some category of problem they have dealt with a hundred times. This can work for them.. Until it does not.
Yes, all said, developers likely are the worst communicators because they over index on their self-ascribed strengths: logic (and logic bullying). Not so much because they aren't smart or capable.
But singling out specific archetypes is an obvious contradiction of the article, which is weird. Author is in the UX design space so likely has particular lived experience with specifically eng orgs.
it's any technical specialist in any field in my experience. my partner is a doctor (not a kind that needs great people skills) and I see the same problems. luckily I have worked with many many developers so it's quite easy to deal with
It is! If I contort a little, the Tower of Babel is the communication problem in reverse. But original sin means we're born sinners so towards effective communication is toward God. But that's not the point of life, the point is serving God as a sinner for salvation (bible stuff, not my point).
> If I contort a little, the Tower of Babel is the communication problem in reverse.
That is what I was referring to. I don't see that you need to contort anything. The story plainly states that without communication problems, man is powerful enough to frighten God, and that the solution God reaches is to introduce communication problems, leaving us stuck in the situation we actually have.
The importance of communication has been recognized for a long time.
I did read your comment as that reference, and I liked it. but I see you got downvoted so I didn't trust myself anymore. thanks for taking the time to confirm.
Yes, pretty aware. Title and subject matter have little overlap. It jumps subjects every 2-3 paragraphs as well and just rambles with spoken thought. Would be best to curate and think than ramble.
Render is really good at this too. I specifically chose "not Vercel" when looking into hosting. Though I haven't tried both to compare: render has been a pleasure, just works, and auto deploys per branch also available.
Now for the criticism: back in the day mint.com was mind-blowing. It's what you always thought you'd wanted. The graphs were interactive and pretty and you really loved seeing them go up. Not so much down. I was so attached to the gamified aspects, much like step counters. They reinforce habits.
My mint journey ended with roughly 5 years or so of data, once they sold to Intuit, didn't like the ads and willingly syncing all my data to mega-corp. Much like Duolingo, it felt good at the time, but I don't know that it did anything for me at all.
Tracking is a double-edged sword: it really does build better habits. It's better to track weight every day for example so you better understand that fluctuations are mostly noise. The daily tracking stuff is entirely useful to get the need to track daily out of your system.
TLDR: checking my net-worth daily sounds like something I should coach myself out from. Ironically that probably takes tools, but the end goal is to not need them.
reply