llmslave2

Checking is good, you should probably check.

Every person I respect as a great programmer thinks agentic workflows are a joke, and almost every programmer I hold in low regard thinks they're the greatest things ever, so while I still check, I'm naturally quite skeptical.

Anecdotal: (of an account) not necessarily true or reliable, because based on personal accounts rather than facts or research.

If you say you drove a 3 minute lap but you didn't time it, that's an anecdote (and is what I mean). If you measured it, that would be a fact.

Not everyone just mindlessly plays the AI slot machine to generate code these days.

One thing I find really funny is when AI enthusiasts make claims about agents and their own productivity its always entirely anecdotally based on their own subjective experience, but when others make claims to the contrary suddenly there is some overwhelming burden of proof that has to be reached in order to make any sort of claims regarding the capabilities of AI workflows. So which is it?

It's not an absolutist statement and it doesn't lead to any of the insane conclusions you came up with. Holding the people running a model liable for what it generates has nothing to do with making tool makers liable.

No, because Grok or ChatGPT etc are not tools, they are services. It doesn't matter if Grok uses an LLM or a bunch of people using Photoshop, if they are outputting illegal content the consequences should be the same.

People don't go after big auto because they sell cars that other people drive. If they suddenly started offering a service where they would drive people around in their cars, and they started crashing into other people, of course they would be responsible for that.

Claude Code didn't exist in January 2025. I think it's a typo and should be 2026.

X needs to be held liable in a criminal court for this. They should not be allowed to hide behind an AI and claim they are not at fault or whatever. They provide a service where users can request images, and the service generated illegal imagery. I will die on the hill that engineers and execs should be heavily fined or going to jail for this.

I feel like the right legal solution is to make the service providers liable in the same way if you offered a service where you got diagnosed by a human and they fucked up, the service is liable. And real liability, with developers and execs going to jail or fined heavily.

The AI models are just tools, but the providers who offer them are not just providing a tool.

This also means if you run the model locally, you're the one liable. I think this makes the most sense and is fairly simple to draw a line.

A diagnostic manual doesn't engage in trying to diagnose you.

I'm not a fan of copyright either but big corporations have abused them for so long, either enforce them to punish these companies or abolish them so these companies die, either one is fine with me. But don't just selectively enforce them to the benefit of these corpos but ignore them when they punish them, that's the worst of both worlds.

The whole point of Tailwind is that it lets you do that. You can debate if Tailwind itself is a good idea but thats not relevant to comparing it to inline styles.

The point being you can't do this with inline styles: "bg-purple md:bg-blue"

> When developers are allowed to use AI tools, they take 19% longer to complete issues—a significant slowdown that goes against developer beliefs and expert forecasts. This gap between perception and reality is striking: developers expected AI to speed them up by 24%, and even after experiencing the slowdown, they still believed AI had sped them up by 20%.

Fascinating that their perceptions basically matched their predictions, and were totally off. Take any claims of "Opus makes me 10x more productive!" with a massive grain of salt, considering they probably read that on X or HN and then their predictions influence their perception.

Can you modify your style tag to make the background turn purple on a mobile device? No? Ok.

You spent many hours of your personal time trying to enable AI companies to better steal OSS work?

Dude get a better hobby or something lol

> Rightly or wrongly, everyone has moved on to using shadcn's system for components.

Everyone in your bubble on X maybe.

If the disruption comes from theft, is the business not viable?

Why? Their software sucks, they're an LLM company not a software company.

I think this is an extremely honest perspective. It's actually kind of cool that it's gotten to the point it can write most code - albeit with a lot of handholding.

Opus 4.1 was released in August or smth.

You can do it multiple ways. Like in go:

   cloj := func() {
     val := 1
     return func(m string) {
       switch m {
         case "inc": val = val + 1
         case "dec": val = val - 1
       }
     }
   } ()
   
   cloj("inc")

In JS you can close upon state and return an object, which is essentially how classes work in the language.

   let cloj = (() => {
     let x = 0; return { inc: () => x++, dec: () => x-- }
   })()
   cloj.inc()

A lot of it is reptile brain fodder but I'd rather spend my time watching brainrot that makes me happy then read ragebait, political takes, etc which genuinely ruin my mental state.

Right but then you expect way more productivity from those teams. I'm wondering where that is.

I find when I'm in a domain I'm not an expert in I am way more productive with the AI tools. With no knowledge of Java or Spring I was able to have AI build out a server in like 10 minutes, when it would have taken me hours to figure out the docs and deployment etc. But like, if I knew Java and Spring I could have built that same thing in 10 minutes anyways. That's not nothing, but also not generalisable to all of software development, not even close. Plus you miss out on actually learning the thing.

And to push this example further, if you can hire 10 developers each commanding 10 reliable junior-mid developers you have a team of 100, which is probably more than enough to build basically any software project in existence. WhatsApp was built with way less than that.

It is, but you get the benefit of shared behaviour and state.

Like an Entity might have a Position, a reference to the World, the Screen, methods for interacting with other entities, etc. You don't get that from simply implementing an interface, although it's not difficult to pass those into the object. A common example I've seen is having every class extend an EventEmitter superclass. You could implement that as part of the interface but that becomes a ton of duplication.

I think of it like this: If you model your domain as something like `A : B : C : D {}` you get all the problems of inheritance, when simply doing D { A; B; C; } gives you the same benefits without the problems. Doing `A : X {}, B : X {}, C : X {}` sidesteps most of the problems with inheritance but gives you some of the benefits as well.

He also has very clear incentives to not only promote it, but believe in it.

Yeah same. Also it completely freezes on my iPhone with sufficient code highlighting. It becomes completely unusable until I restart the App, and then breaks once a new message is sent.

I think we're on the same page re. that study. Actually your link made me think about the ongoing debate around IDE's vs stuff like Vim. Some people swear by IDE's and insist they drastically improve their productivity, others dismiss them or even claim they make them less productive. Sound familiar? I think it's possible these AI tools are simply another way to type code, and the differences averaged out end up being a wash.

Entity systems still rely on inheritance as you typically have an Entity baseclass that all entities derive from. That's just a single level of inheritance. Unity does this through MonoBehavior. Unreal is more inheritance-heavy but developers typically subclass something like `Actor` to one level of additional inheritance beyond the Engine's subclasses. A lot of engines will have multiple superclasses behind a Entity class, but that's an implementation detail of the engine itself and to the game developer, it's treated as a single base class that is typically subclassed a single time for the entity itself.

Even in ECS's you will often find inheritance. Some implementations have you inherit a Component struct, others will have the systems inherit a System class.

I'm sure it's still used today in some engines and by some developers but the overwhelming opinion is that doing something like Entity -> Actor -> Monster -> Orc -> IceOrc is a bad idea. Instead it would be like

   class IceOrc : Entity { components {Health, Enemy, PlayerSeek, Position, etc} }

Where each component is like

   class Health : Component { value = 100 }

And yeah, they favour composition re. Components, it's just that the components tend to inherit from a Component class. But I would still call it composition!