jwpapi

I’m seeing a lot of people that having that train of thought. I think that is a fallacy. I can understand that some LLM execution can be faster, but definitely not all. Agents need to explore, grep and get back up to speed to get context, if you have a good mental model, you can do changes or adaptions in <7s with a bunch of shortcuts or commands.

One could argue to find the <7s commands in your head takes you more mental power than to just wish it in to the LLM and whilst its running you can wish something else in another session, but I’m thinking that the cost of context is more important than the actual execution time for your task. Every extra task gets more expensive. It’s not a ressource where you have a limit, right from the 2nd task the cognitive load increases.

Therefore I’m thinking one task that can be done in one context window without switching is worth a load in these days of constant distraction.

I’m using NEO layout with all the coding keys on layer 3. I’m using both pinkys to jump into layer 3. I can therefore code a lot on home row. I use intellij with two two stroke keybinds (f.e. => Alt + E -> M => Extract Method) and vim motions in editor. I use ai next edit and autocomplete inside editor as I’m right on the loop.

Most changes I need to do are few lines of codes or big architectural changes. I’m at 40k lines of code after 24 months of working that’s 1.5k lines per month and 50 lines a day. If you can write 50 lines a day would you let AI write those or write them yourself.

I challenge anyone to show me a project with a good codebase where the actual loc output is so high that a human couldn’t write it in one hour a day.

I’m not working for a company so my job is to deliver a platform that works for users not to get a paycheck.

It’s exactly the opposite. On small projects I can use heavily because maintanability doesn’t matter on big projects you’ll end up in a deadlock. That’s why we have so many dead projects. People end up with 10x the needed LOCs and changes get incredible slow and tedious.

If i want to have a script that does sth trivial I’m happy to let AI do it, but if I’m building a house that doesnt break hell no.

I don’t know but to me it seems a bunch of people should learn proper typing. There is no way in world that AI is faster in solving/writing problems than you are when you can maneuver your idea/vim properly and have proper domain knowledge and mental model of your codebase. I think it’s genuinely 10x as fast. Just on execution and then if you write it you keep mental model, decide details and you don’t lose context.

Like honestly I’m losing my mind, when people claim I haven’t written code in a year. You had the wrong job your whole life and whilst you think you are so frontier now by using agenst your market value is actually decreasing.

Imagine a painter saying, I’m so happy I don’t have to paint anymore. Or a tennis player. I’m so happay that I don’t have to play tennis anymore.

wtf is going on?

Can you add Zig?

I generally like refactoring too, like cleaning up at home, but if you open up a codebase that has been vibecoded and it seems like it’s a never-ending chain of bad practices leading to performance, security, maintenance problems.

I’ve recently been given the task to work on a fully vibe-coded app. I reduced the code from 140k to 28k lines. This was luckily pre-mvp stage so no users. But if people get stuck at this stage, imagine what’s happening with real workload.

I’ve always been a solo dev, but I’m wondering how in big companies there is even so much to you can actually touch that you need an LLM to do that. Like I can’t delete refactor 120k lines in an established codebase. And one task to fix, takes review time and product time. Like are there now engineers that commit 1k+ lines a day of LLM produced output ?

Bugfixing often is just a bunch of lines, or a replacement of a service often isolated maye 150-200 lines, but I just might be just not experienced enough on these kind of codebases. I can’t grasp the notion of the LLM-multiplex and I don’t know where it’s going.

I have to say I have seen some good solo-dev projects popping up recently (games) that actually got profitable, but usually they were experienced in their discipline before.

Crazy how many engineers in here just say they are using another prompt on top. From my experience that makes things worse. It does abstractions, but the wrong ones. It overcomments, confusing future calls of the LLM.

To me building on multiple scalable systems this has been the most dangerous part of LLMs. On a good codebase it will work good, but it will maek it worse, so you keep using it, till it doesnt work and then you have to pay the bill and fix for what you didn’t build before.

If you put an agent on a fresh codebase 2 things are often given:

-> You have a mental model of the code -> The code is somewhet concise

After multiple iterations both is lost and LLM performance degrades. To solve this you can regular refactor, but it’s not a nice experienc. So my best solution is:

I use LLMs for exploration and for review, but I write the code myself. I find it hard to believe why so many engineers try to avoid it. It’s not consuming much of my time. And it’s actually the most enjoyable part.

Sometimes I race AI i give it a prompt /bug to fix and at the sametime im greping/symboling through the codebase and tryto fix it myself. AI isn’t always faster.

Also controlling input

Most new games are worse than old games anyway

Interesting so it’s supply chain and then you need to calculate how long it can be utilized and for how much you can sell it.

Would love more calculations on that

Buying one of these gadgets killed my brain fog

To me it’s even simpler than that. You use so for exploration and review. Not for writing code.

The issue is that whilst the loops will initially lead to good results they will be less and less as context gets bigger and bigger and tougher to understand for human and AI.

So it depends really on the size of your project.

Whilst I understand cases in which duplication is preffered. I generally think abstractions are underused. Sometimes I would abstract something away that is only done once, not because i want to have less code, but because it allows me to solve bigger problems and when i look at a function I don’t have to worry about it. It allows to create systems. Obviously your abstractions should be good

Seems like I’m the idiot here.

I had frugal stored as more than just economical.

Thanks for your comments :/

Also the explanations are too broad.

F.e. Frugal - Economical with money or goods

I don’t think frugal means economical it means rather over the top …

Yeah I don’t know how to define it properly but I don’t need to learn new words if they don’t even teach the right meaning

Ai slop

Honestly at this point I’m not even sure a non-local startup is a smart move anymore

Like what do we really still need?

Most riches nowadays are created by entertainment or scams :/

IMHO most founder will fail because leaning to heavy into ai and creating a system where they never experience the friction necessary to build the domain knowledge which ultimately could be the deciding factor.

Just think about website design, I don’t think it’s far-fetched to say that a non ai design website will outperform an ai designed one. These percentages add up in multiple disciplines.

I would argue betting against ai is your best chance of succeeding frankly (not in all cases but certainly as displayed here)

Transcription hasn’t become better for 2 years. It was better than before, but there is a ceiling.

I don’t think HN is the right place to post this and also I don’t think the title/slogin as fitting. This might be helpful to beginners, but nobody who’s scared of skill rot, will use this on a mobile app.

Honestly I think there is no benefit in any mobile coding app at all. It makes coding seem way more tedious than it is. I would rather recommend a book, laptop or youtube video than to do coding tasks on a phone keyboard.

Are you guys for real? A mobile app?

Who in the world who’s interested in this would do it on a mobile app.

This is very interesting and the biggest glimpse of hope I’ve seen the last couple months here. I haven’t really paid attention to Fusion even though I got the email. I didn’t even assume it would be comparable.

I wonder if this makes the world a fairer place actually. Because it allows people that are attentive and have time to dig through this to save money. The lowest price would be higher without these patterns.

It’s a polarizing idea, but frankly it’s what the world moves too and seem to work on the market. Some people are lazy or don’t have time and pay more money and some people have less time and dig through dark patterns, collect coupons or utilize ramp up subsidizing.

All those people that actually "work" through it will have less of a prime as if these patterns wouldn’t exist.

The question still remains would the world be a better place without these patterns,as it wastes time and acts against user intent.

It’s just a fascinating question to me, because a lot of things are not as simple as they seem of the first glance.

He’s aware, he just added some curious information.

He’s the mod hero from HN

If the model is so smart why doesn’t it figure it out on its own

Holy shit. I gave it the first actual task I’m facing, it makes me so angry. It just does 7 things more than I asked it fore and it does it so bad. It took 5 minutes and 5 seconds just running time, plus giving me frustration and make me lose my context. Hand-coded I would’ve been done in 3. And it would be code I understand can look at in one year and work on again.

It’s really tough to have sanity fight against hype bros in your head. Probably I should just not visit the internet anymore

To me it’s all just people getting scammed better. With every model it looks better, but it’s at least equally worse to work with, which is the reality it needs to be. It’s less scalable more, code, tougher to understand. Your digging your own grave better kind of.

Honestly all the recent improvements, just seem to be slower and more expensive traded for more accuracy, but the issue is that it needs to be exponentially more accurate to counter the effect of having less of a human in a loop.

Every wrong direction/mistake is more expensive and takes more time to fix. When you have small loops you can catch those mistakes faster and cheaper.

To me we are very far off from economically given long-running tasks to agents.

I don’t even think that Boris is really just one person. He apparently vibe coded Claude Code and is responding on Threads, Twitter, HN and everywhere.

I’m looking for an alternative too..