Live data from Hacker News

Nobody knows how to build with AI yet

worksonmymachine.substack.com

351–360 of 432 posts

Re: Nobody knows how to build with AI yet

#351
post #341

> I'd wander into my office, check what Claude had built, test it real quick. If it worked, great! Commit and push. Do people read the code? Or just test if it work and push? To me, code is like a map that has to be clear enough so other humans can read it to navigate the territory (codebase). Even if it's just two – me and AI agent – working on the codebase, it's not much different from "me and another programmer".…

Stefan Munz called this “YOLO vs tight-leash” at a very entertaining agentic coding meetup in Hamburg recently.

https://bsky.app/profile/stefanmunz.bsky.social

https://www.meetup.com/de-DE/de-DE/agentic-coding-meetup-ham...

Re: Nobody knows how to build with AI yet

#353

I'm loving the new programming. I don't know where it goes either, but I like it for now. I'm actually producing code right this moment, where I would normally just relax and do something else. Instead, I'm relaxing and coding. It's great for a senior guy who has been in the business for a long time. Most of my edits nowadays are tedious. If I look at the code and decide I used the wrong pattern originally, I have to…

I also am enjoying LLMs, but I get no joy out of just prompting them again and again. I get so incredibly bored, with a little side of anxiety that I don’t really know how my program works. I’ll probably get over it, but I’ve been realizing how much fun I get out building something as opposed to just having be built . I used to think all I cared about was results, and now I know that’s not true, so that’s fun! Of cou…

My biggest problem with working LLMs is that they don't understand negatives and they also fail to remember their previous instructions somehow.

For example:

If I tell it to not use X, it will do X.

When I point it out, it fixes it.

Then a few prompts later, it will use X again.

Another issue is the hallucinations. Even if you provide it the entire schema (I did this for a toy app I was working with), it kept on making up "columns" that don't exist. My Invoice model has no STATUS column, why do you keep assuming it's there in the code?

I found them useful for generating the initial version of a new simple feature, but they are not very good for making changes to an existing ones.

I've tried many models, Sonnet is the better one at coding, 3.7 at least, I am not impressed with 4.

Re: Nobody knows how to build with AI yet

#354
post #38

"I'd wander into my office, check what Claude had built, test it real quick. If it worked, great! Commit and push." Man, I'm going to make so much money as a Cybersecurity Consultant!

I tend to generally think the same as you, as I work in the same field. A long time ago I thought to myself, if AI adoption increases exponentially, there is a chance that the amount of security vulnerabilities introduced by it also increases at the same rate.

However, what we are maybe not considering enough is that general AI adoption could and almost certainly will affect the standards for cybersecurity as well. If everyone uses AI and everyone gets used to its quirks and mistakes and is also forgiving about someone else using it since they themselves use it too, the standards for robust and secure systems could decrease to adjust to that. Now, your services as a cybersecurity consultant are no longer in need as much, as whatever company would need them can easily point to all the other companies also caring less and not doing anything about the security issues introduced by the AI that everyone uses. The legal/regulation body would also have to adjust to this, as it is not possible to enforce certain standards if no one can adhere to them.

Re: Nobody knows how to build with AI yet

#355

Earlier quoted context omitted.

Genuinely this is what it sounds like to accept obsolescence and I just can’t understand it. What are you attached to and identify with that you’re rejecting new ways to work? Change is the only constant and tools now look like superhuman tools created for babies compared to the sota at bell or NASA in the 1960s when they were literally trying to create superhuman computing. We have more access to powerful compute an…

I think it's a great technology but if people's ability to put food on the table is compromised what's their incentive not to ventilate people working for AI labs?

If people have shown anything recently it’s the unwillingness to actually do what you just said.

If anyone cared enough to do anything, they would be burning everything down already

It’s a lot of impotent rage because the only virtue people have is consumption, they don’t actually believe in anything. The ones who do believe in fairy tales are part of a dwindling population (religion) that is rightfully crashing.

Welcome to the wasteland of the real

Re: Nobody knows how to build with AI yet

#356

I'm loving the new programming. I don't know where it goes either, but I like it for now. I'm actually producing code right this moment, where I would normally just relax and do something else. Instead, I'm relaxing and coding. It's great for a senior guy who has been in the business for a long time. Most of my edits nowadays are tedious. If I look at the code and decide I used the wrong pattern originally, I have to…

Right, I’ve been using it recently for writing a message queue -> database bridge with checkpointing and all kinds of stuff (I work for a timeseries database company).

I saw this as a chance to embrace AI, after a while of exploring I found Claude Code, and ended up with a pretty solid workflow.

But I say this as someone who has worked with distributed systems / data engineering for almost 2 decades, and spend most of my time reviewing PRs and writing specs anyway.

The trick is to embrace AI on all levels: learn how to use prompts. learn how to use system prompts. learn how to use AI to optimize these prompts. learn how to first write a spec, and use a second AI (“adversarial critic”) to poke holes in that plan. find incompletenesses. delegate the implementation to a cheaper model. learn how to teach AI how to debug problems properly, rather than trying to one-shot fixes in the hope it fixes things. etc

It’s an entirely different way of working.

I think juniors can learn this as well, but need to work within very well-defined frameworks and probably needs to be part of college curriculum as well.

Re: Nobody knows how to build with AI yet

#357
post #311

To me it feels like I’m in the camp of people who has already figured it out. And I have now learned the hard way that it’s almost impossible to teach others (I organized several meetups on the topic). The ability seems like pure magic. I know that there are others who have it very easy now building even complex software with AI and delivering project after project to clients at record speed at no less of quality as…

Just record yourself doing it and post online. If the projects are indeed complex and you’ve found a way to be 20x more productive people will learn from it.

The problem is not having any evidence or basis on which to compare claims. Alchemists claimed for centuries to synthesize gold, if they only had video we could’ve ruled that out fast.

Re: Nobody knows how to build with AI yet

#358

I'm loving the new programming. I don't know where it goes either, but I like it for now. I'm actually producing code right this moment, where I would normally just relax and do something else. Instead, I'm relaxing and coding. It's great for a senior guy who has been in the business for a long time. Most of my edits nowadays are tedious. If I look at the code and decide I used the wrong pattern originally, I have to…

At one hand you get insane productivity boost, something that could take maybe days, weeks or months to do now you can do in significantly shorter amount of time, but how much are you learning if you are at a junior level and not consciously being careful about how you use it, feels like it can be dangerous without a critical mindset, where you eventually rely too much on it that you can't survive without it. Or maybe this is ok? Perhaps the way of programming in the future should be like this, since we have this technology now, why not use it?

Like there's a mindset where you just want to get the job done, ok cool just let the llm do it for me (and it's not perfect atm), and ill stitch everything together fix small stuff that it gets wrong etc, saves alot of time and sure I might learn something in the process as well. And then the other way of working is the traditional way, you google, look up on stackoverflow, read documentations, you sit down try to find out what you need and understand the problem, code a solution iteratively and eventually you get it right and you get a learning experience out of it. Downside is this can take 100 years, at the very least much longer than using an llm in general. And you could argue that if you prompt the llm in a certain way, it would be equivalent to doing all of this but in a faster way, without taking away from you learning.

For seniors it might be another story, it's like they have the critical thinking, experience and creativity already, through years of training, so they don't loose as much compared to a junior. It will be closer for them to treat this as a smarter tool than google.

Personally, I look at it like you now have a smarter tool, a very different one as well, if you use it wisely you can definitely do better than traditional googling and stackoverflow. It will depend on what you are after, and you should be able to adapt to that need. If you just want the job done, then who cares, let the llm do it, if you want to learn you can prompt it in certain way to achieve that, so it shouldn't be a problem. But this sort of way of working requires a conscious effort on how you are using it and an awareness of what downsides there could be if you choose to work with the llm in a certain way to be able to change the way you interact with the llm. In reality I think most people don't go through the hoops of "limiting" the llm so that you can get a better learning experience. But also, what is a better learning experience? Perhaps you could argue that being able to see the solution, or a draft of it, can be a way of speeding up learning experience, because you have a quicker starting point to build upon a solution. I dunno. My only gripe with using LLM, is that deep thinking and creativity can take a dip, you know back in the day when you stumbled upon a really difficult problem, and you had to sit down with it for hours, days, weeks, months until you could solve that. I feel like there are some steps there that are important to internalize, that LLM nowdays makes you skip. What also would be so interesting to me is to compare a senior that got their training prior to LLM, and then compare them to a senior now that gets their training in the new era of programming with AI, and see what kinds of differences one might find I would guess that the senior prior to LLM era, would be way better at coding by hand in general, but critical thinking and creativity, given that they both are good seniors, maybe shouldn't be too different honestly but it just depends on how that other senior, who are used to working with LLMs, interacts with them.

Also I don't like how LLM sometimes can influence your approach to solving something, like perhaps you would have thought about a better way or different way of solving a problem if you didn't first ask the LLM. I think this could be true to a higher degree for juniors than seniors due to gap in experience when you are senior, you sort of have seen alot of things already, so you are aware of alot of ways to solve something, whereas for a junior that "capability" is more limited than a senior.

Re: Nobody knows how to build with AI yet

#359
post #78

I'm loving the new programming. I don't know where it goes either, but I like it for now. I'm actually producing code right this moment, where I would normally just relax and do something else. Instead, I'm relaxing and coding. It's great for a senior guy who has been in the business for a long time. Most of my edits nowadays are tedious. If I look at the code and decide I used the wrong pattern originally, I have to…

Hot take: Junior devs are going to be the ones who "know how to build with AI" better than current seniors. They are entering the job market with sensibilities for a higher-level of abstraction. They will be the first generation of devs that went through high-school + college building with AI.

I think this disregards the costs associated with using AI.

It used to be you could learn to program with a cheap old computer a majority of families can afford. It might have run slower, but you still had all the same tooling that's found on a professional's computer.

To use LLMs for coding, you either have to pay a third party for compute power (and access to models), or you have to provide it yourself (and use freely available ones). Both are (and IMO will remain) expensive.

I'm afraid this builds a moat around programming that will make it less accessible as a discipline. Kids won't just tinker they way into a programming career as they used to, if it takes asking for mom's credit card from minute 0.

As for HS + college providing a CS education using LLMs, spare me. They already don't do that when all it takes is a computer room with free software on it. And I'm not advocating for public funds to be diverted to LLM providers either.

Re: Nobody knows how to build with AI yet

#360

Earlier quoted context omitted.

Which is the real reason agile is so much more effective than waterfall. The beginning of the project is when you know least about your project, so naturally you should be able to evolve the specification.

hmm right, in some ways could argue that AI based development is going against Agile development practices.

Generally I find that agile works because getting a really clear spec is so hard. You’re slowly iterating towards a clear spec. What is a finished piece of software if not a completed spec?

100% agree AI based dev is at odds with agile. You’re basically going to use the AI to fully rewrite the software over and over until the spec becomes clear which just isn’t very efficient. Plus it doesn’t help that natural language cannot be as clear a spec as code.

Post reply on HN