joshuahutt

They didn't think of it "themselves," but they did choose to do it.

Thanks! Are you able to figure it out?

Feel free to message me if you're willing to chat about it. Would love to know if it's actually useful for you.

joshua@huttj.com

You know, I think we’ve reached the point in the divide where it would be more instructive for me to see more examples of how you work, or vice-versa than it would to continue like this.

I get the sense that we are expressing preferences, at this point. I’m sure it would be interesting to watch you do what you do. :)

> this phenomenon occurs because of a lack of tool intelligence in handling tools. What those comments show is that more content is needed on how to survive among numerous tools and how to easily filter tools.

That's fair. Using tools is a skill. We all have different levels of, uh, enthusiasm for exploring and finding them. I just lack the drive to find the perfect tool, similar to how I lost the drive to endlessly customize my phone.

It just feels like a waste of time relative to the other ways I would prefer to spend my time. You could argue that makes me an inferior developer, and I would gladly concede.

What I scrimp on "craftmanship skill points" I gladly put into "empathy and philosophy" ones. Not that they're mutually exclusive, but I got burnt out on trying to solve the wrong problem too many times that I overtrained on connecting with people and trying to ask "are we solving the right problem?"

I guess I could apply that skill to "can I find better tools or use the tools I have better," but that just doesn't feel like a limiting factor, to me.

> You assume that people can know what tools they need.

Not what I was trying to communicate. I was conveying the opposite — you can't know what you need until you're facing a real problem in a real domain, not an imagined one or a simulated environment. So, rather than try to find the best tools for "all time," let the immediate sticking point drive the process of finding and learning tools, evaluated against what solves the problem at hand (with the context of everything you know up until that point, of course).

Very cool! I built a version of this [1], but balked at trying to sell it. This is the third iteration of this idea I've seen so far. Your reply popup is a smart feature and a nice touch! Love it. I love the privacy focus and BYOK, as well.

Congrats on the launch!

Really cool to see graph interfaces for AI having their moment. :)

[1] https://coloring.thinkout.app/

Totally agree. I remember the phrase “learning how to think” being thrown around.

I also remember not being explicitly taught that.

It sort of seems like trying to find enlightenment by chopping wood and carrying water at a monastery.

If critical thinking is something that spontaneously emerges in a learning environment, maybe we shouldn’t sell it as a benefit. “Some students experience deep insight into the nature of the mind. Results not typical.”

Anyone who says “it’s easy” might be having an easy go of it, or they might lack the self-awareness to realize the amount of energy and cortisol they are burning through when they accomplish the task.

“Easy” things today can mysteriously cause burnout tomorrow. It’s easy to mistake the brain chemicals that lubricate effort for lack of friction.

Also, memorizing mental modals has a sort of path dependence to it. Once you have one in your brain, it’s hard to replace, even if it sucks.

You expressed this this much more concisely that I did.

I really enjoyed how the post was laid out —- the structure caught and kept my attention and made the arguments easy to follow.

Unfortunately, I’m not convinced. The author makes a good case for experimentation, but not for “tool maximization.”

I think there is a case to me made for “find tools that do your work for you” —- that’s “buy, don’t build” —- but that case was not made here.

Further, I think that it’s easy to actually overwhelm yourself with too many tools, at which point you’ve exhausted your interest and willingness to learn them. I have several “code time” extensions, which I installed under this exact line of thinking. I still haven’t made the evaluation of which one I prefer. I picked one by default and kept the others “just in case.” And I have plenty of other extensions that I plan to someday evaluate.

I think the best tool use and evaluation comes from a sense of immediate necessity, just like the best learning comes through immediate practice and application.

Everything else is just imagination, which can be hard to sustain and substantiate.

It's like...if "less is more," then "more is less."

Reminds me of a floating point number. The bigger or smaller they get, the less accurate they become.

If you're chunking on a ton of data and tasks, you're getting less out of it. At a certain point, none of it even seems to enter your brain at all.

My thoughts on this are to slow down and document and explore that knowledge and information. If it is really valuable, the "loss" in efficiency from slowing down will be offset by the gain in skill/utility from really grokking the stuff.

If it's not...then there's really nothing "left" on the table — if ever turns out to be valuable, you'll probably come across it again, when needed.

I constantly get a similar feeling. I'm speeding around from task to task, just grasping enough to get the current task done so I can get to the next one and the next one...

And somehow this is value-creating? Apparently it is, but it seems almost accidental, at that rate.

I'd rather slow down and appreciate the value as it moves through me, into whatever I'm doing.

I usually get more from the process, at the same time.

I can see your point, but I think it's worthwhile to understand the full context, even if it's irrelevant on the surface.

I wasn't familiar with von Braun before reading this thread, and I appreciate the extra info. Complex figure. Maybe even a really bad guy. But, also interesting that his work was useful in getting us to the moon.

Maybe we can all appreciate that dichotomy.

Even more interesting to note, is without your initial pushback, I wouldn't have read more detail about him, so I owe your resistance to actually exploring this facet of the man's alleged history to getting me to actually read a bit about it.

That's one way to do it!

Most problems are hard to "solve" because we entertain the delusion of solutions that don't exist — solutions which tie everything together with a nice bow and require no discomfort or negative emotions of any kind.

Alex Hormozi says "the life you want is on the other side of a few hard conversations."

I would channel that to say, "the solution you're looking for is on the other side of a few uncomfortable feelings."

And usually, it's just the fear of the feelings, not the feelings themselves.

True, the apps are all basically converging.

Some great lessons in here.

Particularly liked the one about ambiguities hiding conflict. That’s true in groups and for individuals, in my experience.

When we say “I don’t know,” we usually mean “I haven’t resolved how I feel about this.” Clarity requires drilling down and making decisions, sometimes just about priority. Could be emotions blocking that, for individuals or in groups.

Some things seem inevitable. I've really run myself through the wringer trying to figure out "what could I have done to achieve a better outcome for everyone involved."

I guess success and failure are both group efforts.

Life seems to be a crapshoot for most people. Most people seem to be born into families not adequately equipped to raise children, and the ones that succeed and survive seem to do so despite what they missed out on, developing elaborate coping strategies that survive on into adulthood, which ironically, can lead to more underserved children.

Few seem fortunate enough to find a time to "pause" in their lives, examine what deep seeded issues they have developed from the process of surviving childhood, and finding and embarking on a path to a more balanced and mature, "adult" life.

But hey, it might be a sampling bias. I also imagine there is a silent majority of well adjusted people that don't show up on the internet or the news, projecting themselves all over everyone and everything within their reach.

You may be an outlier.

Many in their 30s are married, mortgaged, and otherwise unable to risk rocking the boat.

How could you, in such a case?

I would love to do the math on this.

The average Janitor I salary in the United States is $34,623 as of February 26, 2024.

Average home price in the United States: $417,700.

Monthly payment for 30-year mortgage is $2,950.

Monthly gross pay is $34,623 / 12 = $2885.25...

Hm...it's literally not doable.

There are very different definitions of "rich."

Take the old comparison between Gates and Jordan. "If Jordan saves 100% of his income for the next 450 years, he'll still have less than Bill Gates has today."

You can become wealthy and comfortable working for a salary. But, the canonical way to get "FU money" is to win the lottery.

Good question.

I expect that we're moving into a phase of AIs talking to AIs, and initially it'll be wasteful (because it'll be mostly English), but eventually, they'll derive their own language and seamlessly upgrade protocols when they determine they're talking to an AI. No clue how that will come about or what that language will look like, but honestly, it's kind of exciting.

Really interesting to think about how they might handle context, as well. Even though we have much bigger context windows (and they'll only get larger), context management is still a resource-management issue, which we'll probably continue to refine, as well. Imagine different strategies for managing both what is brought into the context of each request, as well as what form it could take (level of detail, additional references or commentary on it, etc). Things could get really unreadable even in English, and still be very interpretable for an LLM.

W.r.t. the graph-oriented interfaces, are you thinking something like Node-RED [1]? I'm seeing more and more people mention having LLMs produce non-text or structured outputs, like JSON, UI, and other things. Easy to imagine an LLM that wires together various open-source platforms, on-demand. Something like Node-RED for pipelines/functions, some UI tools for visualization/interactivity, other platforms for messaging, etc...

[1] https://nodered.org/

Just because the process today is "good enough" doesn't mean that it's a worthwhile use of developer time to create that process.

But, you're highlighting one of the challenges of changing the status quo. The "new thing" has to be significantly better than the old, otherwise people won't immediately want to switch.

Similar arguments were probably made when the iPhone removed the physical keyboard.

So you write when inspiration strikes, and you'll re-read and sift through later?

Exactly my point. Why do I need a custom UI for every LOB task under the sun? Just let me use a common interface to address all manner of uninteresting data problems. The UI goes away, or fades into the background, and the focus rests solely on the information I need, and the decisions I make, which I can dive deeper into with a focused AI companion.

Seems like a no-brainer.

Maybe folks LIKE clicking on buttons and going through 10-step procedures to get tasks done.

Some mice like the maze more than the cheese, I guess.

Great point. I have no idea. What are your banking use cases?

For me, it's mostly information I want. I don't really need a full app for that. I want to know:

1) How much money do I have? 2) Did a check I cashed clear yet? 3) Are there any unusual charges? How is my spending this month? 4) Anything I should look into?

For actions I'd want to take:

1) Deposit check 2) Transfer money from account to account 3) Make a payment / authenticate with new EFT payee

All of that could be done conversationally, with a flexible level of detail. The data could be shown on any number of shared interfaces (messaging app, dedicated companion app, etc).

It doesn't obviate the need for software, and there are a ton of software ideas that exist today that will still be useful, as well as ideas that have yet to be discovered that will be useful. But...I expect the LOB app to go extinct in the next couple of decades.

I feel the same way.

I think the immediate future is bright. Some will try to cram this technology into enterprise. It will do well. Those jobs will die. Others will leverage it alongside the more creative engineering tasks—they will thrive.

Eventually, what we call software will change from what it is today into something much more accessible to these types of tools. The plateau we've landed on is just a compromise between the technology, economies, and culture of its time.

As this type of tech pervades our everyday lives, much of the widespread need for specialized software will evaporate. The remaining work will be in the corners or the edges of what's possible—highly technical or vertically integrated work (particularly, hardware-integrated stuff), as well as platform engineering to sustain the new paradigm.

We're solving the wrong problem.

People trying to use cars to pull horse carts are doomed to fail.

Trying to use AI to build the software of yesterday is a waste of time.