aogaili

Yeah but keep in mind this tech only started to work last year? People still figuring it out, and I'm sure we will have more robust tooling, processes around it down the road.

The upside is that we are able to deploy more cognitive power into problems, security, edge cases, something that uses be to scarce. A lot of the people feeling insecure mainly because they benefited from that scarcity. But we will have more software deployed, I'd argue better, and larger, and this means the pie of software is getting bigger, the market is getting larger, deeper into the economy.

Yes of course he is going to use resources around him, that is not the point. It took a leap of imagination to apply it the way he did and think differently.

And this again because it's a solid argument and popular example of human ingenuity.

This is an experimental thought. If people are vibe coding apps without looking at code, the argument here is that maybe ad-hoc prompts is not the best way to capture that because you lose the instructions. So the proposal, why not have those instructions saved as markdown files at least we have a reference in English.

We don't look at binaries, we don't look at assembly, we work with high level languages. The specs were for developers to translate to programming primitives, but if the translation is largely automated, then the specs will become the code and we will need better ways to manage those, and I think the IDEs are gradually trending that way, look at all the most recent agentic dev tools, it surely follows that trend.

With respect to not having this piece on HN. If the author is seeing many organizations doing this practice, then why he would not share that empirical observation? is it only because it is against your pure world and abstractions? Just the recent leak for the Muse agent shows that most of the system behaviour is written in markdown.

Whether you like it or not, technology never care about purest and idealist, it evolve under pressure of deliveries and pragmatic choices, and if there is such a pressure, which the author claims to be, then HN is the medium to share it.

Traditionally docs were for humans as a reference.

This is not doc, this is an .md file as a src to be used by LLMs to generate code. Therefore they are src files but in english.

1. he is saying md/english is the new source code.. 2. yes - it is different that is geared towards english and very well supported by LLMs that is why it is being used in memory and instructions 3. llms are deterministic enough to translate adequately described specs into working system, the idea here is reason in md for core flow etc, and then verify with test cases

this not perfect but he is describing a real trend, so listen with open mind.

You missed the entire point of the post..the author is arguing docs in md are the src...

You are generalizing all llm-aided building to "vibing", which is not the case..and most engineering are based on science but they are not scientist (i.e discovering new science).

I think of a lot of people with this mindset never built anything substantial with the new tools to understand the new set of challenges with these processes and systems. It makes sense given your/their negative take on it which doesn't allow any room for exploration.

I think it is mostly pride issue honestly, because you use terms such "insult" and "real engineers etc". Some are learning and using those new tools and others are refusing given their pride. Similar to how Blackberry executives dismissed iPhone as a toy, and the rest is history.

https://www.news18.com/photogallery/business/in-2007-blackbe...

I invite you to build something substantial with those tools on the side.

"Engineering is the practical science of designing, building, and testing structures, machines, systems, and processes to solve real-world problems"

Did this system go through: design? yes, building: yes, testing: yes, is it a system: yes, does it solve real-world problem: yes.

but markdowns and LLMs with their fuzzy probabilistic feelings are beneath you i assume? you can ignore the fact that we have intelligence deployed to the billions, understand english, follow instructions..yeah, in case you missed, machines can now understand english better than you and me.

I think the current architecture is limited.

To quote Einstein directly:

-----

Viereck (Interviewer): How do you account for your discoveries? Through intuition or inspiration?

Einstein: Discussing intuition and his confidence in relativity, noting he was convinced the 1919 eclipse would confirm his hypothesis.

Viereck: Then you trust more to your imagination than to your knowledge?

Einstein: I am enough of the artist to draw freely upon my imagination. Imagination is more important than knowledge. Knowledge is limited. Imagination encircles the world.

-----

I think we need more breakthroughs to build AI that can "draw freely upon imagination" to quote Einstein describing his process.

That is just my guess.

Good analogy, yeah make sense.

Here is his quote:

"Imagination is more important than knowledge. For knowledge is limited, whereas imagination encircles the world,” means that facts alone only describe what currently exists, while imagination allows us to discover what is yet unproven or unbuilt"

This probably sums up the current AI limitation nicely.

just because humans couldn't solve does not mean the necessary technique were not already discovered...we have agents that don't get tired and has access to all humanity knowledge, the building blocks could be there already..

this is not moving the goalposts, this is try to understand what this tech truly able and not able to do.

Actually I think this is true, remove the s.

Reminds of what Einstein said, imagination is more important than knowledge..might be his deepest insight ever.

I don't know..I doubt for example it can come up with special relatively if it has knowledge up until 1905.

But I think that is what makes it so good at coding, because coding and building software in general has a lot of repeated problems in different context. Same thing for human lives, many think their story or situation are unique, but reality is that the shape of human life has been repeated many many times.

I'd say novel math or scientific theories..let us say we send a robot to space, and we ask to build a colony. A lot of the challenges this robot will face will be novel, it could use inspirations of what humans did on earth, but it might get stuck when things don't work as expected and training data has nothing to build on..but then again we might teach it how to run experiments etc, which would result in data that it can use..but some of those experiments might require imagination or breakthrough in understanding..my guess is that it will get stuck there...

If the problem was solved by anyone before or if a similar problem has been solved, then LLMs seem to be able to solve them which is an astonishing piece of technology.

I'm personally not sure if it can come with original thinking and techniques to solve completely novel problems. For that, some imagination and thinking outside the box are required, and I doubt the current architecture can do any of this.

Will be downvoted for sure, but here we go:

They can't think that a software can be written, designed and maintained in English or higher constructs.

It is binary of either vibe coded app, or worshipping the code that they worship (and I spent 20+ years on)..the industry is moving on faster than most can wrap their heads on, but for those who understand software engineering was always beyond and above code, they will adapt, meanwhile, those who built their entire identity and skillset around managing code will struggle. There will be a place for those people, but it will be niche and specific, and we won't need as many.

This is really an interesting experiment.

Agreed - they don't seen to have "agency" in them, or someone put a dog in them.

On that we agree then. I also don't want to go through mountains of tangled text written by an AI.

But what if the AI models improve their writing style considerably to match that of the best authors? which I think is plausible soon.

I feel in the near future, what really matters the most is the seed and the dialog/back and forth more than then who wrote what. And that the best content would be a by product of human/machine interaction atleast given the current generation of tech.

Until perhaps, in the the not so distant future, the math can encode our taste, judgments and develop imagination, then maybe the best human wouldn't be able to create anything better than the machine. But then again, we want to communicate the inner state of human being, because we want to build relationship, so content for consumption might be dominated by machines, but communication as way to build relationship might stay genuinely human...but even that might change, what if machines eventually become better at relationships than humans? that could be how AI truly "kill us"..I think within few decades we will discover that our intellect was a short period of cosmic evolution, and we will accept our fate as animals with analog organic intelligence that helped to bootstrap what comes next, this might be scary but humbling, and I think it's inevitable.

Let me leave with something we agree on at least:

"The speed alone doesn't translate to productivity and productivity alone doesn't translate to quality."

Trying to understand your position.

Let us say someone had few good ideas, and seeded them into a prompt, and after few back and forth, web searches via agent, feedback from the author, a piece of work was produced and the author decided to share it as a blog.

This is not much different than how people are producing original work LLM in areas such as math.

Would you object to reading their work because it was a byproduct of collaboration between AI/Humans? What about songs? movies? math proves? and software produces as such?

you too :)

Sorry - I really don't think you know what you are taking about.

Because they can easily get outcompeted by those who care about software/output and use the latest tools? might as well code in assembly and brag about it.

I'm not here condemning people who use or not use. We have a new tech, for anyone who have been in the field long enough, it is nothing short of magic was has been accomplished in the last few years.

I could turn around 10K lines of code per day (I know it's not the best measurement but it does capture size to some extent) when I was not able to pull more than a 100 LOC. Let us say that most of it work, and there are few rough edges, a senior programmer can follow the shape of the code, and understand where to tweak and where the LLM get stuck. So this is basically like having racing engine compared to running.

"if one person knows how to code, they don't need an LLM. I've tried using all of them on my job, and I will give them a second chance time by time (to see if the claims made by these big tech hold up) and ALL of the time I've didn't noticed any speedup compared to coding manually."

I mean, have you truly tried? do others thing this is true? I'm truly astonished if that is majority experience, I think we need to get surveys on this.

People flag/downvote what they don't like without explaining much, and a lot of it are just feeling based/snap reactions.

HN is not that rational of a discussion form but there are some good articles/comments so worth being around.

I think people are judging mainly the UI of the app. This is closed code app so they don't know, but they are judging by patterns in the UI and/or wording of documentation. And I think it is mainly tech or artists or whoever else is impacted by the AI usage.

That is not say there are really mindlessly produced apps out there. But the comment made it sound that anything LLM-aided is negative.

I hand written each one of them, I think they are full of typos and grammatical errors as well since English is not my first language.

I assume you are saying that because I apologized. I apologize for sounding like AI, I assure you it was hand written and I put thoughts into those comments.

That is the original comment: " for what seems to be a very much LLM-aided app? "

The author mentioned LLM-aided app, not even AI assisted; nor vibe coded hence my reaction. I don't have insecurity from using LLM nor from coding manually. But I noticed a trend in people thinking and biases and it threw me off hence the comment.

My original comment was heavily downvoted and furthermore some of my comments were accused of being written by AI meanwhile I'm writing it by hand. Again, people are taking tribes/camps, if you speaking of insecurities, it actually the opposite clearly, many programmers are worried of being displaced and automated. And I do understand the concern, I'm just stating the fact that one can have very deeply thoughted LLM-aided app.

I get it - I think there mis-communication here.

My comment was about not equating every LLM assisted app as poorly thought of. Your comment is about this specific app, and I personally would not install this app regardless of how it was coded.

But again in terms of security since you brought it, I'd argue that having LLM assisted coded app might be secure than manually coded application given the recent advancements. Again, this is a generic statement, not specific to this app.