[applfanboysbgon]

> but I finally feel like I'm _good_ at programming, which is insane

Yes, it is insane. You couldn't torture this confession out of me. But that's the drug they're selling you, isn't it? You don't even write code, but you're getting a self-inflated sense of worth. It must be addicting! Of course, whether or not the programs you prompt are actually good surely has no relation to whether you feel they're good, since you're not the one writing them, and apparently were not capable of writing them before so are not qualified to review them very much.

> having tools that can finally match the speed my ideas come to me

Anyone can be an "ideas guy". We laughed at those people, because having ideas is not the hard part. The hard part was in all of the hundreds and thousands of little details that go into building the ideas into something actually worthwhile, and that hasn't changed. LLMs can build an idea into a prototype in a weekend. I am still waiting to see LLMs build an idea into something other people use at scale, once, ever, other than LLM wrappers. Either every person who is all-in on vibes only has ideas that consist of making .md files and publishing them as a "meta agent framework", or LLMs are not actually doing a great job of translating ideas into tangibly useful software.

[542458]

> Anyone can be an "ideas guy".

I disagree with this. I've worked with amazing "ideas guys" who just cranked out customer insights and interesting concepts, and I've worked with lousy ones, who just kinda meandered and never had a focused vision beyond a milquetoast copy of the last thing they saw. There's a real skill to forming good concepts, and it's not a skill everyone has!

[applfanboysbgon]

I do agree that having good ideas is a skill in its own right. But people with bad ideas are idea guys too! You see them all the time in the indie game development scene in particular. "I need a programmer, and an artist, and a composer, to build this amazing idea for me!", together with an 8 paragraph wall of text (the paragraphs are if you're lucky) describing the idea, and as you'd expect from somebody who couldn't be bothered to develop a single skill, their game ideas are exactly as good as their programming, art, and music.

I find that the strength of people's ideas tends to be highly correlated with their overall skills. I don't know that you can develop the capability for good ideas without getting your hands dirty learning a field, experimenting, absorbing all kinds of information and understanding what really goes into the making of a good idea. In that way, the person with good ideas always ends up being more than just a ideas guy. They don't just have good ideas, they have good ideas and the skills to back them up. Whereas the "ideas guy" label is usually applied to people who have nothing to bring to the table other than their ideas, and wouldn't you know it, they aren't nearly as good as they think they are.

[Aurornis]

I think the Product Manager title was (and still is) one of the most abused titles in tech. A great product manager is indispensable for setting product direction in a way that can't be accomplished by others doing it part-time or advocating for their own needs. I've worked with some truly great product managers.

I've also worked with a lot of awful product managers. The product manager title is squishy enough that it gets assigned to people with charisma or confidence without actual skills to follow through. A bad product manager can blend in to a company for years by relaying ideas around from one group to another and having ChatGPT write documents. The engineers on the ground see the incompetence long before it becomes undeniable at the higher ranks.

When I read Hacker News and other sites I suspect a lot of engineers have only ever worked with bad PMs from the latter category.

[angrymouse]

What do you think the good ones do? And how do they set direction in a way that’s good compared to a bad one?

[Aurornis]

Great product managers know the current customers, industry, potential additional customers, and the company very well. They communicate well. They can optimize the match between customer needs, marketing benefits, internal company priorities, and reasonable developer asks.

The best ones I’ve worked with have been so good that their roadmaps and conclusions feel obviously correct, and everyone has bought into the direction because their input was considered.

[paavope]

The good ones have original thoughts and can combine knowledge from different domains in nontrivial ways

[moduspol]

Anyone can be an "ideas guy" because there's no failure event that stops you. Contrast this with being a plumber. Not anyone can be a plumber.

[tekacs]

I think that the point about building with agents though. Your ideas meet reality sooner and you actually get feedback on whether they are worth anything or not. So you're not really being an ideas guy in the sense of just throwing ideas out there. You're being an ideas guy in the sense of testing your ideas, which is really the essence of what building startups is: figuring out what people want.

[moduspol]

That's true. I was just responding to the post above, which seemed to be inferring a different meaning (i.e. that there are no bad or good ideas guys) than how I interpreted it.

[jmuguy]

A lot of this is also missing understanding the software we're creating. I have a deep knowledge of our SaaS because I've spent years working on coding it. If I had been prompting an LLM this entire time, I can't imagine I would actually have near the same understanding. That is assuming purely planning and prompting could actually result in a product that's in active use for years and not just a pile of prototypes which apparently desperately needed to be created and were just waiting for AI to come along to make it possible.

I've been using AI tools more but this idea of never actually writing any code seems way too black and white to be serious.

[supern0va]

>Anyone can be an "ideas guy".

I think there's way more nuance to this than you're willing to admit here. There's a significant difference between the guy who thinks "I'm going to make X app to do Y and get loaded." and the person who really understands the details of what they want to create and has a concrete vision of how to shape it.

I think that product shaping and detail oriented vision of how something should work and be used by people is genuinely challenging, wholly aside from the lower level technical skills required to execute it.

This is part of the reason why I wouldn't be surprised at all to see product manager types getting more hands-on, or seeing the software engineering profession evolve into more of a PM/SDE hybrid.

[cgg23]

Disagree massively.

A proper PM should be moving towards owning design and marketing pieces - not production of software. Software is a means to package an experience captured by the design and communicated via marketing. It's that simple.

Most PMs don't match this description. So I understand the frustration's of engineers who have had to work with PMs.

[supern0va]

A well constructed BRD is a very large chunk of the context needed for more successful use of an LLM. You're welcome to disagree, but I've found increasingly that the work artifacts from PMs are becoming even more essential to the actual development.

If you understand the design and user experience end to end and can express that effectively in writing, that's...your agent context. Why do a context hand-off to another human, or at least why remain as silo'd as we have historically been?

[thangalin]

> LLMs are not actually doing a great job of translating ideas into tangibly useful software

Here is the source code for a greenfield, zero-dependency, 100% pure PHP raw Git repository viewer made for self-hosted or shared environments that is 99.9% vibe-coded and has had ~10k hits and ~7k viewers of late, with 0 errors reported in the logs over the last 24 hours:

https://repo.autonoma.ca/repo/treetrek

[BoorishBears]

https://repo.autonoma.ca/repo/treetrek/blob/HEAD/pages/Templ...

Did it really have to be zero-dependency...

[dvfjsdhgfv]

Frankly, I created dozen of such projects in the last weeks. Recently I just deleted them all. I feel like there's no point. I cancelled my Claude subscription, too.

I got back learning from books and use LLMs for "review my code in depth and show me its weak points" occasionally.

[baq]

LLMs in teacher mode instead of solver mode can be great. ("review this change" is kinda sorta teacher mode.)

[tovej]

How is this greenfield?

[thangalin]

How is it not?

You can trace the back commits to the first to show that it was started from scratch:

https://repo.autonoma.ca/repo/treetrek/commits/c7742cb3c580d...

[tovej]

It's using a mature data model from an existing framework (git), and it's essentially a simpler clone of other similar projects.

That's brownfield to me. Greenfield would develop a completely new system. This is a utility for an existing system, one whose design is clearly a copy of existing utilities. Both of those make this brownfield.

[thangalin]

I'm building something from scratch, with no existing code base, and no requirement to integrate with or extend an existing implementation. The only constraint is Git's raw file format. Brownfield, to me, means constraints from existing software. It gets a little fuzzy, but no existing code base was used, no existing architectural constraints were imposed, and I was free to design the implementation from scratch; a greenfield implementation of a legacy protocol.

[tovej]

You are using git's data model. And all you're doing is visualizing it. It's not greenfield.

[thunky]

> Anyone can be an "ideas guy". We laughed at those people, because having ideas is not the hard part.

Sure it's easy to create bad ideas. Not easy at all to create good ones.

[xg15]

> LLMs can build an idea into a prototype in a weekend

Just to nitpick, because I think the difference is relevant: "Idea to prototype in a weekend" was possible for a spirited coder already before LLMs.

Now it's "Idea to prototype in a few minutes".

[bartread]

> You don't even write code, but you're getting a self-inflated sense of worth.

That’s because when it comes to delivering value, code doesn’t matter: outcomes do.

If I spend 10 hours hand coding something versus prompting an LLM to create a solution that delivers the same outcome in a few minutes, and I can get that solution into production in under an hour from the moment my fingers first touch the keyboard to start writing the prompt, well, whilst these solutions might both deliver the same value, the ROI differs significantly.

[awesome_dude]

> because having ideas is not the hard part.

I agree. It's the "buy in" from the market.

The biggest names in Software Products have (other peoples) ideas to sell, they're selling the buggy versions of those ideas - Microsoft, Salesforce, even early Facebook, these weren't triumphs of 'monk-like discipline' in the code. They were triumphs of market buy in and timing.

[paultendo]

Anyone can be an "ideas guy", very few are good at it.

"I am still waiting to see LLMs build an idea into something other people use at scale" - so Microsoft using Claude Code doesn't count?

[applfanboysbgon]

Nope. I specifically excluded LLM wrappers, which I think is a fair qualification for a "first useful software at scale". If it turns out that LLMs can produce useful things that aren't LLM wrappers, then maybe later we can evaluate whether LLM wrappers are worthwhile. But if LLM wrappers are only used to produce other LLM wrappers, which are used to produce other LLM wrappers, it's merely indicative of a pyramid scheme wherein people are trying to sell you on hype because they can't sell you anything that actually produces utility in the real world (browsers, compilers, IDEs, production databases, music production software, photo editing software, Excel, viable Discord replacement, any of the reasons people used computers as tools to accomplish things).

On the note of Microsoft specifically, they've shipped a critical OS-destroying bug every month for several months straight now, and people seem to be generally in agreement that Windows 11 has only been going further and further downhill. I have literally not seen a single person with a positive opinion on anything W11 or associated programs have done in the last 6 months. Which does not create a compelling case for translating LLM wrapper into real-world useful code.