Rendered at 20:47:15 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
digitallogic 7 minutes ago [-]
> You have enough budget for only the first floor, but you have a big family, and you know you’ll want a second one in a couple of years.
> Adding the infrastructure to support a 2nd floor is MUCH cheaper right now than it will be when you actually want that 2nd floor.
The problem with this thinking is it requires certainty about the future. It's much cheaper right now IF AND ONLY IF you end up needing the thing. If you don't need it, then you've threw time and money down the drain.
Where I think this analogy weakens is you probably have far more certainty of whether or not you want a big family then you do on whether or not a new product line will see major adoption.
tripleee 23 minutes ago [-]
This is all caused because no-one understands the purpose of quality in software
Low quality = cascading bugs, issues, slow to iterate and add or change features
This is just as true for human written as it is for AI
Instead we have everyone giving up on code quality as if it was just "beautiful code" perfectly indented that was only there for people to ooh and aah at
SoftTalker 4 minutes ago [-]
Low quality = you will sooner or later be writing a "We take security seriously" letter and buying credit monitoring for all your customers.
mehagar 20 minutes ago [-]
Even if you do use AI tools to help you write the code, at some level you have to specify what the program's output should be for every possible input.
By loosely specifying things in a prompt, there's simply not enough context for the AI tool to know the "right" output to produce for all possible inputs. What's "right" is often subjective anyway ("Should this button be red or blue?").
miranaproarrow 1 hours ago [-]
My manager who vibe coded our entire webapp in claude design. Has difficulty understanding why its still not production ready.
My job is to wire to our backend data, and a lot of these wiring require me to be in there and actually think about the features. These take time, and I just haven't figure out a way to speed this process up with Claude.
godwinson__4-8 26 minutes ago [-]
Why is this reassuring?
Why won't smarter and cheaper models in the future be able to automate this part for your manager as well? How novel is the feature set? Is it he has a knowledge gap or the model is incapable of something? What expertise are you bringing to bear that is beyond the scope of a future harness/model? Why wouldn't such a model simply fill in the blanks for your management, perhaps observing a diff of whatever you did? How do you verify the correctness of your thinking? Why could a future model not replicate this process?
I am just very puzzled by these sort of takes as we approach the end of 2026.
tripleee 15 minutes ago [-]
Because smarter for an LLM isn't operating on the same scale as human intelligence
Making a calculator a billion times "smarter" isn't going to make it able to wash dishes
godwinson__4-8 6 minutes ago [-]
This would be a great point if his manager asked him to wash the dishes. Who knows, in 10 years time if he finds himself with such a job he might consider himself lucky.
Anyway I hope I get an answer to my actual questions. Engaging with your "it's just a calculator" denialism is an obvious dead-end. Have a good day buddy.
tripleee 2 minutes ago [-]
Completely missing my point there. I wasn't saying it's a calculator. I was saying it's not a human intelligence and there's no reason to think it'll stand in for every responsibility we have.
Name me one human that can describe grandmaster level chess strategy but also loses to a random-only chess bot - that was the case for LLMs for a long time
My point is LLMs aren't humans. They're not a toddler slowly getting smarter, and when they're smarter they'll be able to do everything a human can do. It's a different scale entirely.
Axsuul 11 minutes ago [-]
Why isn't a LLM as smart as a human? Therein lies your problem.
platevoltage 31 minutes ago [-]
Yeah, I have 2 clients that are now obsessed with vibe coding. They seem to understand the realities.
holoduke 47 minutes ago [-]
On the other hand. If his tool does the job why not. If you asked a 90s engineer how javascript triggers millions of cpu instructions for just a few code steps he would call you crazy.
scottyah 34 minutes ago [-]
Is it big data? Claude should be able to tell you what to do and give you scripts to deploy anything behind a web app.
jbverschoor 10 minutes ago [-]
Medical doctors mostly follow standard procedure and decision trees.
andsoitis 16 minutes ago [-]
I don't know that saying "this work is hard" is enlightening.
More useful would be to be able to explain at some high level what the the inherent and accidental complexity is, the tradeoffs to navigate, long-term vs short-term decisions, etc.
Saying "it is hard" makes the audience think you're less of an expert in your domain and they are then inclined to find someone who doesn't say "this work is hard".
etothepii 55 minutes ago [-]
> "Never really finish building it" is the key insight.
The problem with software is that it is never done. There is always another feature you could have and worse than building a property the work is only done by the people on the outside.
randusername 39 minutes ago [-]
I think it's deeper than that, once you know software is never done you have to design for constant change.
When clients ask why something takes so long, I explain that I'm not building what you asked for today, I'm building something that will be easy to turn into what you asked for today and possible to turn into whatever you ask for tomorrow.
Fr0styMatt88 3 minutes ago [-]
AI has vastly changed the shape of what that looks like though. There are whole classes of refactoring work that are much cheaper and quicker to do with agents. Integrating a protocol client library say, or swapping one library for another are now potentially hour-long instead of days-long tasks, especially when you have test coverage to back you up (which AI also immensely helps you with).
LastTrain 49 minutes ago [-]
We’re in the self driving car stage right now. A Waymo can drive itself but the belts and suspenders involved are more expensive than a normal car.
high_na_euv 37 minutes ago [-]
More expensive?
mikestew 22 minutes ago [-]
Not OP, but… It can drive itself…mostly (the “belt”). And when it doesn’t, you need remote drivers (the “suspenders”) to get it unstuck. I don’t need that with the car I drive myself, and it probably won’t be needed with self-driving cars (waaaay in the future, IMO).
joshdavham 43 minutes ago [-]
This is definitely getting my favorite. I’m also going to shamelessly steal this house analogy.
Thanks for writing this!
scottyah 37 minutes ago [-]
I've been using it for years. "Let's decide where we want the plumbing to go before pouring the slab", or "let's not focus on where the couch will go before we paint the walls". Or when a 'genius cowboy dev' discovers a super fast way to get from the 2nd floor to the kitchen by cutting a hole in the floor despite all the leaks it causes and how many other people have to work around the change.
davidhegarty 29 minutes ago [-]
The house analogy is great.
The extreme is the Winchester Mystery house.
…which is always how I explain legacy code.
vanschelven 1 hours ago [-]
TBH I think we still need to explain this to ourselves first.
jmclnx 1 hours ago [-]
My experience over many decades is this:
* If a business person thinks a change or new program is very easy to do, it is really a very hard project.
* If a business person thinks the change or new program us hard to do, usually it is a trivial project.
For me, this has been true for well over 40 years. I never use any kind AI for my work, it did not exist before I retired.
etothepii 54 minutes ago [-]
This is is relatable but I think the issue is that they are uncorrelated.
If it's easy and the business thinks it's easy it gets done. If it's hard and the business thinks it's hard it doesn't.
tristor 11 minutes ago [-]
My experience matches this also. My observation is that most business people think things they know they don't know are hard, and things that they think they do know are easy. My additional observation is that AI tools make business people think they know a lot more things, so they consider a lot more things easy, when they are not. AI tools are a machine that makes business people Dunning-Kruger-max.
The problem with this thinking is it requires certainty about the future. It's much cheaper right now IF AND ONLY IF you end up needing the thing. If you don't need it, then you've threw time and money down the drain.
Where I think this analogy weakens is you probably have far more certainty of whether or not you want a big family then you do on whether or not a new product line will see major adoption.
Low quality = cascading bugs, issues, slow to iterate and add or change features
This is just as true for human written as it is for AI
Instead we have everyone giving up on code quality as if it was just "beautiful code" perfectly indented that was only there for people to ooh and aah at
By loosely specifying things in a prompt, there's simply not enough context for the AI tool to know the "right" output to produce for all possible inputs. What's "right" is often subjective anyway ("Should this button be red or blue?").
My job is to wire to our backend data, and a lot of these wiring require me to be in there and actually think about the features. These take time, and I just haven't figure out a way to speed this process up with Claude.
Why won't smarter and cheaper models in the future be able to automate this part for your manager as well? How novel is the feature set? Is it he has a knowledge gap or the model is incapable of something? What expertise are you bringing to bear that is beyond the scope of a future harness/model? Why wouldn't such a model simply fill in the blanks for your management, perhaps observing a diff of whatever you did? How do you verify the correctness of your thinking? Why could a future model not replicate this process?
I am just very puzzled by these sort of takes as we approach the end of 2026.
Making a calculator a billion times "smarter" isn't going to make it able to wash dishes
Anyway I hope I get an answer to my actual questions. Engaging with your "it's just a calculator" denialism is an obvious dead-end. Have a good day buddy.
Name me one human that can describe grandmaster level chess strategy but also loses to a random-only chess bot - that was the case for LLMs for a long time
My point is LLMs aren't humans. They're not a toddler slowly getting smarter, and when they're smarter they'll be able to do everything a human can do. It's a different scale entirely.
More useful would be to be able to explain at some high level what the the inherent and accidental complexity is, the tradeoffs to navigate, long-term vs short-term decisions, etc.
Saying "it is hard" makes the audience think you're less of an expert in your domain and they are then inclined to find someone who doesn't say "this work is hard".
The problem with software is that it is never done. There is always another feature you could have and worse than building a property the work is only done by the people on the outside.
When clients ask why something takes so long, I explain that I'm not building what you asked for today, I'm building something that will be easy to turn into what you asked for today and possible to turn into whatever you ask for tomorrow.
Thanks for writing this!
…which is always how I explain legacy code.
* If a business person thinks a change or new program is very easy to do, it is really a very hard project.
* If a business person thinks the change or new program us hard to do, usually it is a trivial project.
For me, this has been true for well over 40 years. I never use any kind AI for my work, it did not exist before I retired.
If it's easy and the business thinks it's easy it gets done. If it's hard and the business thinks it's hard it doesn't.
Check out Synthetiq if you want to actually get into production
Like in 1 to 5 years, vibe coding without looking at the code will likely be a lot better.