cautiouscat

Similar to someone just scrawling a sandwich board sign in chalk

As opposed to what? This is usually a sign of quality. If it’s in chalk it’s because it changes as the restaurant experiments and tries new things.

The posters all look good

Maybe I’m misunderstanding but I haven’t seen many that I’d say look “good”. Especially food related ones.

I have a few friends I’d describe as high up in the restaurant industry. They’ll usually be skeptical of a menu with photos unless it’s a mom and pop place that’s been around for decades.

There’s a big reason more expensive restaurants don’t have pictures on their menus, even when they’re the best equipped to ensure your meal matches the picture.

Calling it "AI" was possibly a net-negative but we don't know yet.

I’m not sure it’s net negative or not. I’ve found that it’s reductive though. We have this really broad field of artificial intelligence reduced down to at worst a “slop machine” and at best a single tool.

Imagine being a CS professor that studied AI in the 90s and how you have to over explain you don’t mean LLM chatbots to a layman.

Those people are not just on Twitter. They’re here on HN, they’re at work, they’re at your next social gathering.

I’ve found them to be unavoidable to some degree.

C-suites. Marketers. People with stock portfolios. Banks. Politicians.

So all people that don’t understand the thing being hyped.

I hope neither wins, and open models win.

i dont think there is any software on the planet that i would consider "truly life changing", so i find it a bit weird to hold ai up to that standard.

I think the author made this point because earlier they mention how people tell them AI changed their life.

So I started asking a simple question whenever someone told me AI had changed their life: ‘Cool. Show me.’

Nintendo gets a lot of flak for how they treat consumers and how litigious they are. However I get the impression they treat their employees very well in Japan. Like when the Wii U flopped, execs took a pay cut to avoid layoffs.

No company is perfect, but Nintendo seems like an example some C-suites should follow.

I have no concrete scientific evidence of this - my own personal vibe metric of “is a model good enough” is, “do I have to double-check it against an API model”, and GPT-OSS was the first one where I started doing that a lot less often.

The good old butt dyno!

I’ve been eyeing local models more and more with Anthropic squeezing more and more on the subscriptions. A few comments on HN had me waiting until they improved more but this article makes me wonder if I should reconsider that.

I’ve been doing some pretty niche development using a game and a script extender for said game. If these models can handle that, I’d feel good about switching.

Maybe it’s just me but it’s still hard. Writing code wasn’t hard before. Honestly putting up guard rails is harder than writing it yourself. It just may be faster now.

Getting proper requirements, knowing what to make, update, the domain knowledge, satisfying customers was and still is the hard part.

Maybe the recent final update to Destiny has already taken over my brain but if Marko is a Destiny fan, he has a great GitHub username.

This is an extremely detailed article on every level and I can’t wait to deep dive into it. Marko really nailed the “old” look but it still looks fresh and new.

I assume consumers aren’t a big note in their bottom line. I’m not actually very sure about that, just an assumption.

What I wonder however is if these tools will become something I use at work only. $100/month is already a massive stretch budget wise. If these models keep devouring tokens there’s no way I’d get the same usage time out of them for $100 in usage credits.

I just don’t think I’d use them much at all at home.

I didn’t say that and I don’t have a feeling on that either way. But this is a limited time trial and calling it out as such is valid.

Is it nice we get the trial? Sure. Is it also a common play in the playbook of tech companies? Yes.

In the automotive world we have benchmarks in HP/torque with the dyno. That’s expensive though, so many depend on their “butt dyno” to judge if their fresh new parts and tune made a difference.

I’m curious how this will feel to my code “butt dyno”. I haven’t noticed much between Opus and Sonnet. I’m comparing this difference to the early days of Claude in 2025. It does what I need and both need a little bit of correction and whatnot. Benchmarks are nice, but I want to see how this feels. Looking forward to trying it later tonight.

It’s an interesting thing to bring up because it’s this classic thing we’ve seen for decades now.

The ramifications go beyond the individual which is why I assume they mentioned it. They don’t need to use it/not use it for it to have interesting implications.

How is someone showing a 3D render with no products or services to buy from advertising to me? In addition, why does that matter if I enjoy the content?

It’s not “just” advertising. Again this is nuanced.

I agree but there’s definitely room for nuance. I follow a lot of artists because I genuinely like seeing their work. I follow a lot of miniature painters for their tips and tricks. I follow my close friends to see what they’re up to.

I think the folks you’re talking about are influencers. Which I wholeheartedly agree with your take in that case.

I don't know if y'all have tried it, but it now produces really good stuff.

Does it? It produces passable stuff that is fine. However the lack of passion and care completely disinterests me.

I’m more of an “AI centrist”, as I think the topic is extremely nuanced. As with most tech hype, there tends to be a black and white “AI good” or “AI bad”. I think reality is somewhere in the middle, personally.

Let’s face it: by the time I manually ship version 1.0 of a product, the AI-assisted version could have been deployed 10x faster. By then, enough real-world feedback would have surfaced to identify the major issues, and tools like Claude Code would make it possible to fix and ship version 2.0 at an incredible pace.

It’s takes like this that remove the nuance completely and ignore so many facets of the debate. That being said, let’s assume this is true because I think vibecoding a CRUD app does make this realistic on the face of it. When I say vibecoding I mean prompting and dropping, not reading the code.

You do your adversarial reviews with multiple agents, you have your UX agent look over it, your security agent etc. Under the hood there are architectural issues. The code is probably passable, but rough.

You release, customers start using it for their business that they depend on for income. Issues start cropping up, you burn more and more tokens to fix the issues as they come up. Expedience starts sacrificing quality even still, architecture (if there was any) starts being violated and it degrades more and more.

I consider myself a professional, I would never want to end up in a situation like this for mission crititcal products. So, what do I do? I read the output, I make sure I understand it. Why? I care about my customers and secondarily I’m the one with the pager when something breaks down.

Now, for some fun hobby project to track my hobby paints for Warhammer… who cares? I agree. I have used Claude for such projects and not really cared. But your statement does not hold up in the enterprise world with mission critical software.

At some point, execution speed starts to matter more than the elegance of the code.

This is reductive. You’re assuming people’s concern is “elegance”. It isn’t solely elegance. It’s domain understanding. It’s quality over all. It’s being a professional.

Writing the code was never the slow down for large scale enterprise products.

Problem is once we got them, we realized they are not all that.

Isn't this just the hype cycle? [1]

Fake edit: I know its not a perfect model.

1: https://www.gartner.com/en/research/methodologies/gartner-hy...

Every time I think I am adept in git, something like this is shown to me. I really should read into it more lol.

Haven’t you heard? If you don’t adapt now you’ll be left behind, never to be able to work again! Copilot? That’s so last year. Agentic engineering? You’re already late!

This quote from the authors friend really hit home with me.

“If you’re going to use an LLM to write me an email, I’d much rather you just send me the prompt; at least then I’d have an idea of what you actually meant to say.”

I’m not saying there’s no merit in adding a bit of politeness and professionalism to your communication, which I’m sure the prompt itself lacks. However the root of what you’re trying to convey is the prompt, wrap that in a header and a signature. Not only are we talking as humans, we’re also communicating directly.

Also I just find it a little insulting if someone sends me an AI response. I don’t know why, maybe because it feels not genuine.

Yeah I do find myself leaning back into those tools. For awhile I’d just prompt to rename something. But when it’s my own tokens I’m paying for, I prefer the fast and free option :)

I agree with the article, though I will say with an agentic workflow I feel more tired at the end of it than I would doing it by hand. Maybe it’s the constant reading and digging in the generated code, or the constant context switching while waiting for it to think/generate. Or it’s both.

Woah! I loved this game on Steam. If anyone likes factory games (Satisfactory or Factorio) and programming this is a must try. Also got a bit of idle game in the mix. Surprisingly immersive too for a mostly text game.

Yeah but these models are the worst they’ll ever be! They’ll get better! You need to give it better context! Did you try multiple agents?

Sarcasm aside, I am just so tired.

I think this is the part that kills me. This is what many grunts, including myself said from the start. More PRs and more code does not equal value for the customer.

I’ve also been finding that “Spin a cadre of agents to design/implement a feature from a concise spec” is really difficult. It’s been faster (for me) to do what you said and do a hybrid.

I’ve been trying out this cadre of agents idea with PR stacking and while I think it’s going to end up working fine, it took so much massaging to get it to where I needed it to be. Whereas with the hybrid approach, the problem space is a lot narrower and easier for me to define and the LLM to implement.