sbarre

I came to the comments to see the discussion and almost all of them are just complaining about LLM-assisted writing.

It's exhausting and tedious, like people nitpicking grammar.

It's also off-topic. I'd love it if HN banned (or strongly discouraged) this kind of repetitive low-value off-topic meta-discussion.

We get it, LLMs are used to write now. Some people don't like it. No need to broadcast that dislike every time, it adds noise to the discussion. :-(

(yes I realize I am also adding off-topic noise but this thread was nothing but that, so I guess I am on-topic until actual Postgres discussion starts).

That's fair, I guess I was really reacting to the narrow gatekeeping-like case the OP was advocating, where time spent/invested - or only doing things a certain way - was correlated to legitimacy and being able to claim you "made" a thing.

I never said that. I said I don't want to see change for change's sake.

If you can come up with a better experience and it's a worthwhile change that materially improves the product, I will take it of course.

On the software side iOS introduces new useful features for sure, I don't deny that. They also took a nice simple flat UI and glass-ified it in a really dumb way. And the OS is so bloated that I lose 10-15% of my storage to packages and installation files (seriously go look up how much of your phone's storage is used by "System files").

But on the hardware side these days they're just fiddling with the camera and moving the buttons around, and that's not something I want to have to care about when I upgrade.

This is of course all subjective, I'm sharing my view here, not implying that I speak for the world.

Really? You care about some stranger's work and how they created it?

Pro tip: you shouldn't.

Care about your work if you want, but "caring" about how someone else makes things and how they talk about it is just being a judgemental busybody and again, gatekeeping.

As for my comment, I stand by it.

If I made something genuinely useful, then it should not matter if it took me 5 minutes or 5 days to make it.

You'll never convince me that more time spent making something (all other factors being equal - yes, quality matters) gives it more value or credibility.

I think you're being pedantic to the point of losing all credibility. And you're gatekeeping in the worst possible way.

Your argument that using an LLM means you didn't "make" a thing could just as easily be used to say that if you used a framework or a library, you also didn't "make" a thing, because you didn't write all the code yourself and you didn't understand everything.

Would you say the authors of YT-DLP didn't "make" anything because they are a wrapper over FFMPEG and CURL?

If you produce something useful (even just to yourself), you "made" a thing.. It has a purpose, and it's useful. Who cares how you made it or how long it took?

For example I've made plenty of bash scripts over the years that were effectively thin wrappers that combined other tools, but they did something novel and useful that saved me tons of time, and I've shared those as gists or in other ways.

Some of these scripts took me mere minutes to make. I didn't use an LLM to make them, but the "heavy lifting" definitely wasn't in my script. No one ever showed up to berate me and try to tell me that I didn't actually produce anything useful in any of these cases.

So this "in the past" that you imagine where people were held to some bullshit standard for what is accepted as "making" a thing?

That past doesn't really exist, and if does where you are, it sucks.

That said one could argue that phones are now "solved" and the idea of iterating and changing just for the sake of changing is unwelcome. Much like laptops?

I don't want my next phone to be something I need to figure out all over again. I want the buttons in the same place, the OS to work the same way..

My phone is just another thing in my daily life like my car or my coffee machine. The less I have to think about any of those things - vs. just using them and getting on with my day - the happier I am.

I suspect that instead of treating the US as a bully, and pushing back, we are treating the US as a troll, and just looking away instead.

We'll go trade with other countries and stop giving the troll the attention it craves.

> You are not entitled to compensation for everything shitty that happens in the world.

This is true, but not relevant here?

If you pay for a service, and you don't get that service, are you implying that you should just be SOL?

If the plane has an issue, and the pilot rightfully lands it for safety concerns, but the paying passengers don't get where they are going, that sounds like the airline's problem to me, not the passengers' problem.

At the very minimum the passenger should be refunded for their ticket, because they didn't get what they paid for.

There are already too many negative consequences in the world of commercial transactions that the end-consumer gets saddled with simply because they don't have the leverage, money or time to fight for redress.

This would not be enforceable. Do you understand the scale of Youtube?

Also why would YT get involved in the content of videos themselves, beyond legal moderation requirements?

That's a slippery slope in itself, and it would just lead to a cat-and-mouse game where creators try to incorporate sponsorships in less obvious/visible ways, which is a net bad thing for the audience.

Now at least creators are required to disclose when their videos contain sponsored segments or paid advertisements. What you propose would take away that accountability.

As it stands, you can see when a video includes ads, and you can choose to not watch it. That's your choice.

> Other services (e.g. YouTube Premium) reduce ads, but do not eliminate them, no matter how much you pay.

Hmm curious to know where you live that you still get Youtube-supplied ads with YT Premium?

Because "ad-free" is literally the headline feature.

Unless you're talking about in-video ads and sponsorships added in by the video creators themselves, and then that's not something in YT's control (although they provide the "skip commonly skipped sections" feature in Premium that helps with this).

What you pay(paid) for cable TV was never enough to actually cover the total cost of the service you were receiving.

You were splitting that cost with the advertisers.

This is not a defence of advertising, just a reality check on this bad example.

For sure, I was not implying ELK was a replacement, it's just been good to me for some types of flowcharts that get messy with the standard Dagre layout ...

Excellent work on Line9 BTW, it looks fantastic. :-)

FYI for any new or casual Mermaid users, it comes with a built-in alternate layout called `elk` that I find does a much cleaner job on complex flowcharts.

See docs here: https://mermaid.ai/open-source/config/layouts.html

> how much do we gain when Sol scolds Fable?

You might be surprised at how much benefit you get from the model council[0] pattern.

The common pattern I've seen is "build with Claude, review with GPT", or vice-versa.

It's been proven to be very effective.

0: https://www.google.com/search?q=model+council+pattern&udm=14

> There are standards in language that are not all “left means right for me so you cannot assume when i say right it is right and not left”

Yes of course there are words that have very clear meaning, and that's not the case here.

"startup" and "legacy" - used in the context of this discussion - are not words like "left" and "right" where everyone has a universal agreed-upon understanding of their meaning.

2M lines of code is 15 people committing ~26k lines of code per year (~100 lines per working day) for 5 years.

15 people is a pretty small startup, what if this is a 50-person startup?

Doesn't seem like that much to me, depending on what you're building and the size of your team.

> Are we in school debate club?

Not that I know of but that's the conclusion I drew from your statement.

It's not a cheap shot unless you took it personally?

I suppose I could have said "the fact that OP's explanation of how they work did not lead you to conclude they were in fact guiding their LLM usage quite a bit tells me that perhaps you have not been working with LLMs in any advanced capacity".

For the SDLC comment I admit it was a broader statement (based on observing people generalizing that "LLMs produce bad outputs") and not specifically aimed at you, and I didn't make that clear, so my bad.

Man, so many people in this thread just arguing pointless semantics, making weirdo absolutist (and incorrect) statements.

Accept that other people may ascribe different meanings/interpretations to words than you, and that if your reading of their statement doesn't make sense to you, perhaps you are simply reading it wrong.

Trying to hold someone else to your definition of words suits what purpose exactly? Are you just trying to "win" ?

> You didn't say anything positively or negatively regarding this so I made an assumption that you were using the LLM relatively unguided

I feel like this statement betrays your lack of advanced experience coding with LLMs.

OP's elaboration of the steps they are going through (planning, agreeing on plan, getting one LLM to draft execution plan, approving it, then executing with a separate LLM, then reviewing/testing) made it super obvious to me that they are guiding their LLMs quite considerably as part of their work.

Anyone making blanket statements about LLMs producing garbage is just telling on themselves about not having proper SDLC practices in place.

Who is "we" here?

This is about one company bending the knee, not an entire industry or population.

Even simpler: I wish banks would allow you to set up a requirement of MFA for transactions over a certain amount (with everyone's consent of course).

My parents are not yet a concern for this stuff, but I imagine eventually they might be.

So I would get a notification on my phone to approve the transaction/withdrawal.

That's an interesting perspective..

I feel like everyone I know/knew who was really into Airtable was pretty sophisticated and used it for complex data wrangling that was beyond the typical tools they had access to.

But they were often solo operators for that data because whatever they were wrangling wasn't worth putting into a database or investing in more robust tools (from a company perspective)..

So perhaps you are correct.

It's also a byproduct of the most successful user acquisition model to be honest.

Getting users is hard, especially on the Internet where your audience is global, and competition is fierce. Word of mouth or user advocacy has always been the best cost-to-value marketing tool.

So starting out by offering things for free or at a loss has been the go-to strategy forever.

But (as we all know) that's not sustainable, so there's pretty much nowhere to go but down, from a value-to-user perspective.

Does that apply here?

We're talking about abstracting generic OS windowing/multiplexing for what sounds like an agent-based development workflow modality where you're referring to what's happening in the panes/tabs/windows instead of the containers themselves.

We're not talking about software abstractions.

Some needed context is that article is over 3 years old.

If you like terminals and tmux, can I suggest you spend a few hours playing with herdr? It clicked for me in a way that a lot of other orchestrators didn't.

There is value in abstracting the underlying generic systems into more context-relevant primitives for people who just want to get shit done in that context.

Why not meet people where they are at?

If this product isn't valuable, then it will fail. I suspect it will not fail.

How about we don't trust either of the proprietary shovel salesmen?

If you want a local and open source option (MacOS only at the moment though), I've been happily using Keyscribe for dictation, which is built on Moonshine I believe.

https://rsperko.github.io/keyscribe/

Because (A) it has an OpenAI logo on it and (B) they made $13B and lost $21B last year?