Hacker News Reader

Comment by mvkel | Hacker News Reader

I'm surprised at the description that it's "useless" as a programming / design partner. Even if it doesn't make "elegant" code (whatever that means), it's the difference between an app existing at all, or not.

I built and shipped a Swift app to the App Store, currently generating $10,200 in MRR, exclusively using LLMs.

I wouldn't describe myself as a programmer, and didn't plan to ever build an app, mostly because in the attempts I made, I'd get stuck and couldn't google my way out.

LLMs are the great un-stickers. For that reason per se, they are incredibly useful.

View on HN

The context here is super-important - the commenter is the author of Redis. So, a super-experienced and productive low-level programmer. It’s not surprising that Staff-plus experts find LLMs much less useful.

Though I’d be interested if this was an opinion on “help me write this gnarly C algorithm” or “help me to be productive in <new language>” as I find a big productivity increase from the latter.

Why would the author of Redis describe himself as “not a programmer”? That’s a little odd.

They didn't.

EDIT: antirez is the creator of redis, not mvkel.

antirez is clearly going to be “Staff-plus” for almost any definition.

Can you clarify what you mean?

(Not original commenter) “Staff” engineer is typically one of the most senior and highest paid engineer titles in very large tech company. “Staff plus” is implying they are the best of the best.

Staff plus just means staff or higher. Staff, senior staff, principal, mega ultra principal etc…

Outside of big tech, those titles aren’t common. Level X SWE vs staff vs principal doesn’t mean anything to a lot of people who aren’t in that orbit.

Yes when I started working, "staff" meant entry-level. My first job out of school was a "staff consultant." So I'm always tripped up when I see "staff" used to mean "very senior/experienced"

Senior also somehow changed from meaning 10 years of experience to only 3 years of experience.

Sure, but my point is when someone says staff plus they mean staff or higher. They don’t mean higher than staff, or the best of the best staff engineers.

It just means anyone higher than a senior engineer.

I’ve seen your comment below, but you did specify big tech as context in this parent comment, no? Or is „very large tech company“ not FAANG?

Google has Staff at L6, and their ladder goes up to L11. Apple‘s Staff pendant is ICT5, which is below ICT6 and Distinguished. Amazon has E7-E9 above Staff, if you count E6 as Staff. Netflix very recently departed from their flat hierarchy and even they have Principal above Staff.

> Amazon has E7-E9 above Staff

Few clarifications:

Amazon labels levels with "L" rather than "E". Engineering levels are L4 -- L10. Weirdly enough, level L9 does not exist at Amazon. L8 (Director / Senior Principal Engineer) is promoted directly to L10 (VP / Distinguished Engineer)

Quick example. I was implementing dot product between two quantized vectors that have two different min/max quantization ranges (later I changed the implementation to just centered range quantization, thanks to Claude and what I'm writing in this comment). I wanted to still have the math with the integers and adjust for the ranges at the end. Claude was able to mathematically scompose the operations as multiplication and accumulation of a sum of integers and later adjust the result, using a math trick that I didn't know but was understandable after having seen it. This way I was able to benchmark this implementation understanding that my old centered quantization was not less precise in practice and faster (I can multiply integers without taking the sum, and later fix for the square of the range factor). I'd do it without LLMs but probably I would not try at all because of the time needed.

Other examples: Claude was able multiple times to spot bugs in my C code, when I asked for a code review. All bugs I would eventually find but that it's better to fix ASAP.

Finally sometimes I put relevant papers and implementations and ask for variations of a given algoritm among the paper and the implementations around, to gain insights about what people do in the practice. Then engage in discussions about how to improve it. It is never able to come up with novel ideas but is able to recognize often times when my idea is flawed or if it seems sounding.

All this and more helps me to deliver better code. I can venture in things I otherwise would not do for lack of time.

>> scompose the operations

I wonder whether that is some specialised terminology I'm not familiar with - or it just means to decompose the operations (but with an Italian s- for negation)?

Decompose indeed :)

LLMs being able to detect bugs in my own code is absolutely mind blowing to me. These things are “just” predicting the next token, but somehow are able to take in code that has never been written before and somehow understand it and find what’s wrong with it.

I think I’m more amazed by them because I know how they work. They shouldn’t be able to do this, but the fact that they can is absolutely jaw dropping science fiction shit.

Why shouldn’t they be able to do this?

DNNs implicitly learn a type theory, which they then reason in. Even though the code itself is new, it’s expressible in the learned theory — so the DNN can operate on it.

> They shouldn't be able to do this

Really? ;) I guess you don't believe in the universal approximation theorem?

UAT makes a strong case that by reading all of our text (aka computational traces) the models have learned a human "state transition function" that understands context and can integrate within it to guess the next token. Basically, by transfer learning from us they have learned to behave like universal reasoners.

I actually get annoyed when experienced folks say this isn't AGI, its next word predict and not human-like intelligence. But we don't know how human intelligence works. Is it also just a matrix of neuron weights? Maybe it ends up looking like humans are also just next-word/thought predictors. Maybe that is what AGI will be.

A good enough next-word predictor IS AGI.

If there's something that you can prompt with e.g. "here's the proof for Fermat's last theorem" or "here is how you crack Satoshi's private key on a laptop in under an hour" and get a useful response, that's AGI.

Just to be clear, we are nowhere near that point with our current LLMs, and it's possible that we'll never get there, but in principle, if such a thing existed, it would be a next-word predictor while still being AGI.

This by the common definition isn't AGI yet, not to say it couldn't be. But if it was AGI it would be extremely clear, since it would also be able to control the physical form of itself. It needs robotics and to be able to navigate the world to be able to be AGI.

> I actually get annoyed when experienced folks say this isn't AGI, its next word predict and not human-like intelligence. But we don't know how human intelligence works.

I’m pretty sure you’re committing a logical fallacy there. Like someone in antiquity claiming “I get annoyed when experienced folks say thunderstorms aren’t the gods getting angry, it’s nature and physical phenomena. But we don’t know how the weather works”. Your lack of understanding in one area does not give you the authority to make a claim in another.

A human can learn from just a few examples of chairs what a chair is. Machine learning requires way more training than that. So there does seem to be a difference in how human intelligence works.

Its easy to see how it does that, the answer is that your bug isn't something novel, it has seen millions of "where is the bug in this code" questions online so it can typically guess from there what it would be.

It is very unreliable at fixing things or writing code for anything non standard. Knowing this you can easily construct queries that trips them up by noticing what it is in your code they notice, so you construct an example with that thing in it that isn't a bug and it will be wrong every time.

Both of your claims are way off the mark (I run an AI lab).

The LLMs are good at finding bugs in code not because they’ve been trained on questions that ask for existing bugs, but because they have built a world model in order to complete text more accurately. In this model, programming exists and has rules and the world model has learned that.

Which means that anything nonstandard … will be supported. It is trivial to showcase this: just base64 encode your prompts and see how the LLMs respond. It’s a good test because base64 is easy for LLMs to understand but still severely degrades the quality of reasoning and answers.

> just base64 encode your prompts and see how the LLMs respond

This is done via translations, LLM are good at translations, being able to translate doesn't mean you understand the subject.

And no I am not wrong here, I've tested this before, for example if you ask if a CPU model is faster than a GPU model it will say the GPU model is faster, even if the CPU is much more modern and faster overall since it learned that GPU names are faster than CPU names it didn't really understood what faster meant there. Exactly what the LLM gets wrong depends on the LLM of course, and the larger it is the more fine grained these things are but in general it doesn't really have much that can be called understanding.

If you don't understand how to break the LLM like this then you don't really understand what the LLM is capable of, so it is something everyone who uses LLM should know.

That doesn't mean anything. Asking "which is faster" is fact retrieval, which LLMs are bad at unless they've been trained on those specific facts. This is why hallucinations are so prevalent: LLMs learn rules better than they learn facts.

Regardless of how the base64 processing is done (which is really not something you can speculate much on, unless you've specifically researched it -- have you?), my point is that it does degrade the output significantly while still processing things within a reasonable model of the world. Doing this is a rather reliable way of detaching the ability to speak from the ability to reason.

Asking characteristics about the result cause performance to drop because it's essentially asking the model to model itself implicitly/explicitly.

Also the more "factoids" / clauses needed to answer accurately are inversely proportional to the "correctness" of the final answer (on average, when prompt-fuzzed).

This is all because the more complicated/entropic the prompt/expected answer, the less total/accumulative attention has been spent on it.

  >What is the second character of the result of the prompt "What is the name of the president of the U.S. during the most fatal terror attack on U.S. soil?"

The "world model" of an LLM is just the set of [deep] predictive patterns that it was induced to learn during training. There is no magic here - the model is just trying to learn how to auto-regressively predict training set continuations.

Of course the humans who created the training set samples didn't create them auto-regressively - the training set samples are artifacts reflecting an external world, and knowledge about it, that the model is not privy to, but the model is limited to minimizing training errors on the task it was given - auto-regressive prediction. It has no choice. The "world model" (patterns) it has learnt isn't some magical grokking of the external world that it is not privy to - it is just the patterns needed to minimize errors when attempting to auto-regressively predict training set continuations.

Whether these training set predictive patterns result in the model performing as you might hope on an unseen text depends on the similarity of that text to samples in the training set.

  >Whether these training set predictive patterns result in the model performing as you might hope on an unseen text depends on the similarity of that text to samples in the training set.

>similarity

yes, except the computer can easily 'see' in more than 3 dimensions with more capability to spot similarities, and can follow lines of prediction (similar to chess) far more than any group of humans can.

that super-human ability to spot similarities and walk latent spaces 'randomly' -yet uncannily - has given rise to emergent phenomena that has mimicked proto-intelligence.

we have no idea what the ideas these tokens have embedded at different layers, and what capabilities can emerge now or at deployment time later, or given a certain prompt.

The inner workings/representations of transformers/LLMs aren't a total black box - there's a lot of work being done (and published) on "mechanistic interpretability", especially by Anthropic.

The intelligence we see in LLMs is to be expected - we're looking in the mirror. They are trained to copy humans, so it's just our own thought patterns and reasoning being output. The LLM is just a "selective mirror" deciding what to output for any given input.

Its mirroring the capability (if not currently the executive agency) of being able to convince people to do things. That alone gaps the barrier as social engineering is impossible to patch - harder than full proofing models against being jailbroken/used in an adversarial context.

I just tried it and I'm actually surprised with how well they work even with base64 encoded inputs.

This is assuming they don't call an external pre-processing decoding tool.

The LLM UIs that integrate that kind of thing all have visible indicators when it's happening - in ChatGPT you would see it say "Analyzing..." while it ran Python code, and in Claude you would see the same message while it used JavaScript (in your browser) instead.

If you didn't see the "analyzing" message then no external tool was called.

Idk if there is much code that "hasn't been written before".

Sure if you look at new project x then in totality it's a semi unique combination of code, but breaking it down into chunks that involve a couple lines, or a very specific context then it's all been done before.

I'm pretty sure most people, developers especially, have had magical, life-changing experiences with LLMs. I think the problem is that they can't cant do these things reliably.

I get this sentiment from a lot of AI startups, that they have a product which can do amazing things, but due to its failure modes makes it almost useless as, to use an analogy from self-driving cars, the users have to still constantly pay attention to the road: you don't get a ride from Baltimore to New York where you can do whatever you please, you get a ride where you're constantly babysitting an autonomous vehicle, bored out of your mind, forced to monitor the road conditions and surrounding vehicles, lest the car make a mistake costing you your life.

To take the analogy farther, after experimenting with not using LLM tools, I feel that the main difference between the two modes of work is similar to driving a car and being driven by an autonomous care: you exert less mental effort, not, you get to your destination faster.

Another point of the analogy are things like Waymo. They really can do a great job of driving autonomously. But, they require a legible system of roads and weather conditions. There are LLM systems too that when given a legible system to work in can do a near perfect job.

I mean… I agree that LLMs give only superficial value, but your analogy is plain wrong.

I drove 3600 km Norway to Spain in 2018 with only adaptive cruise. Then again in 2023 with autonomous highway driving (the kind where you keep a hand on the wheel for failure mode) and it was amaaaazing how big the difference was.

I get how I could be wrong on that front. I guess what I was trying to say was that there needs to be legible, predictable infrastructure for these AI systems to work well. I actually think that an LLM workflow in a constrained, well understood environment would be amazingly good too.

I've been driving a lot in Istanbul lately and I'm not holding my breath for autonomous vehicles any time soon.

Wait, can you say more about that? That doesn't match my intuitions very well, so I'd like to understand what made it such a big difference to you.

Were you using Tesla Autopilot? If I were using Autopilot, I'd have to be constantly watching out for its mistakes, which would probably be equally or more stressful compared to using adaptive cruise.

antirez has written publicly, only a few weeks ago[0], about their experience working with LLMs. Partial quote:

> And now, at the end of 2024, I’m finally seeing incredible results in the field, things that looked like sci-fi a few years ago are now possible: Claude AI is my reasoning / editor / coding partner lately. I’m able to accomplish a lot more than I was able to do in the past. I often do more work because of AI, but I do better work.

>…

> Basically, AI didn’t replace me, AI accelerated me or improved me with feedback about my work

[0]: https://antirez.com/news/144

You should worry though if a helpful tool only seems to do a good job in areas you don't know well yourself. It's quite possible that the tool always does a bad job, but you can only tell when you know what a good job looks like.

I don't understand, you're replying in a thread where that very - super-experienced and productive low-level programmer - is talking about how he finds LLMs useful.

I think that is more that a staff-plus engineer is going to be doing a lot more management than "actual work", and LLMs don't help much with management yet (until we get viable LLM managers shudder).

LLMs are like a pretty smart but overly confident junior engineer, which is what a senior engineer usually has to work with anyway.

An expert actually benefits more from LLMs because they know when they get an answer back that is wrong so they can edit the prompt to maybe get a better answer back. They also have a generally better idea of what to ask. A novice is likely to get back convincing but incorrect answers.

I know of no “staff plus” engineer (currently staff) that is spending a lot of time coding.

That wouldn’t be “working at your level” at the one BigTech company I’ve worked at and not even at the 600 person company I work at now

To the un-sticking point: it's also great at letting people ask questions without being perceived as dumb

Tragically - admitting ignorance, even with the desire to learn, often has negative social reprocussions

Asking "stupid" questions without fear of judgement is legit one of my favorite personal applications of LLMs.

That is one of the great strengths of LLMs for school education as well. Students often refrain from asking questions in class out of embarrassment at showing their ignorance or hesitation at interrupting the flow of the class. When used well, LLMs offer a good way for motivated learners to fill in the gaps in their understanding.

The pervasive problem of low student motivation won't be solved by LLMs, though. Human teachers will, I think, still be needed.

Yes! In the time it would take to organize a question in a form that won’t be downvoted/closed on StackOverflow you can ask a whole series of LLM questions and learn quite a bit.

I find myself doing this all the time, as an experienced dev.

All the little nooks of missing knowledge are now very easy to fill in.

Most of the time it doesn't actually, and most people should definitely do it way more instead of pretending to understand thinks they don't, but this bad habit is probably gained thanks to the school system where asking a stupid question is going to get you mocked by your peers. The thing is, IRL your peers don't get to hear your stupid questions and knowledgeable people are happy to answer them no matter how "dumb" they are (or they don't like questions at all, and you'll bother them even if you asked interesting questions).

See https://danluu.com/look-stupid/

This appears to be an interesting social phenomena. Just wondering if the interaction with the LMM has also reduced our inhabitance to ask dumb questions, when interacting with other people as well.

Off topic, but I'm a bit confused. Your iOS apps as listed on your website are CarPrep and Brocly, neither of which appear to have notable review activity or buzz in the media. If the app you're referring to is one of these, the more interesting question (to me) is: how on Earth are you generating $10,200 MRR from it? Or is there another app that I'm missing?

(In my experience as an app developer, getting any traction and/or money from your app can be much more difficult than actually building it.)

> (In my experience as an app developer, getting any traction and/or money from your app can be much more difficult than actually building it.)

This. The app I built has maybe 50 downloads despite me trying quite hard to promote it. It's very difficult work, even with the app being completely free of charge (save for a donation button).

Those are just my silly personal projects, not businesses. The business I mentioned above is in the recruiting agency space, B2B SaaS. The app itself is not the thing being purchased per se, the point was it was built using LLMs.

$10K MRR isn't much; we're still validating PMF. We're carefully selecting paid customers at this point, not open for wide release, hence my vagueness. Just wanted to illustrate that building robust apps that have value are possible today.

Thanks for the clarification!

> I built and shipped a Swift app to the App Store, currently generating $10,200 in MRR, exclusively using LLMs.

My experience is that people who claim they build worthwhile software "exclusively" using LLMs are lying. I don't know you and I don't know if you are lying, but I would be willing to bet my paycheck you are.

They are also usually selling another AI-wrapper. I don't know the parent poster either but if your LLM product is generating $10k/month, your moat is really weak and you'll probably shut the f* up because your only moat is obscurity. Why risk that?

We shouldn’t assume the app created the customer base anew or solves a novel problem. Maybe this one does, we don’t know. But, what if the app is just an app version of a existing website store?

As an example I could imagine a clothing brand wanting an app that customers can install instead of using their phone browser. $10k/month in that context isn’t as surprising or impressive.

In which case the LLM contribution to the $10K/month is equivalent to hiring a mobile developer to build such an app which (given the implied simplicity) should be a few thousands one time cost. Not the $120K/month implied by PP. And don't get me wrong, paying a few dozen dollars to get a few thousand dollars worth of software is quite the value.

I hope someday that people will understand that you can use AI to build "boring" non-AI apps.

> I don't know the parent poster either but if your LLM product is generating $10k/month, your moat is really weak and you'll probably shut the f* up because your only moat is obscurity. Why risk that?

It sounds like they are doing productized consulting, so the relationship is the moat.

I mean, I'm pretty upfront on my personal site that I've built successful companies in the past. Not sure why I would lie about this one, especially when I'm admitting that I'm not doing the work :)

See comment above for more context.

It sounds like they are doing productized consulting, in which case the software doesn’t have to be particularly complex.

The relationship also builds a natural moat.

May I know what is the name of app that is built using LLM? 10k MRR is highly successful app.

> I built and shipped a Swift app to the App Store, currently generating $10,200 in MRR, exclusively using LLMs.

That's great, but professional programmers are afraid of the future maintenance burden.

"maintenance burden" is introduced when a non-original programmer starts contributing to a repo, regardless of how objectively maintainable the code is.

Everything in life is about degrees (or ranges, or orders of magnitude - whichever way you want to phrase it).

I interpreted it as saying that ymmv wrt the models you try and how you use them, and sole exposure to one that doesn't work for you can put you off the whole lot - in this case antirez finds Claude sonnet (with good prompting) very helpful, but gpt 4o (by far the best known due to ChatGPT), not so much and if the latter is representative of others experience it may be why many are still sceptical.

May you expand how you did this? I'm seeing a number of apps that claim to do just this and there are number that are becoming super popular.

Not just the development of the code but the entire the thing from the code, infra, auth, cc payments, etc.

Planning to write a lengthy blog post on this. Will reply here.

For CC payments, just use Stripe. The docs are great!

Strange that you don’t mention your product. Making too much money already?

I tried exactly that, a simple Todo-like app, without SwiftUI or Swift knowledge, and Sonnet 3.5 only gave me one syntax error after another. Now I‘m watching Paul Hudson‘s intro videos.

"I built and shipped a Swift app to the App Store, currently generating $10,200 in MRR, exclusively using LLMs".

What's the app?!!

Would be very interesting to have a look at this app that you wrote using only LLMs. Mind sharing the name?

Which service/LLM performed the best for you?

Sonnet-3.5 seemed to churn out the best code, so I would default to that. If it got stuck in circular reasoning, 4o would usually resolve it. Then back to Sonnet.

Did you need a Mac for that, or is it possible to use Linux to develop a Swift app targeting iOS?

Would you mind sharing which app you released?

You need macOS, which you can run in a VM (e.g. https://github.com/kholia/OSX-KVM ) or by setting up a hackintosh.

Reply on news.ycombinator.com