TheSamFischer

It’s not a goal post. It was literally a fucking benchmark of the very first LLMs.

any update? It’s still glitching. I thought it was easy.

> There was never really a need to have finely crafted, artisanal code in these code bases

Oh if we only had a middle ground between hitting the slop button versus hitting every key manually.

> Yes, sure, maintainability, yada yada. For most code out there, that never mattered anyway.

I’m so glad we have an expert who knows what’s best for “most code out there” gracing this thread with his presence.

> The idea that someone could just replace it in a matter of days is wild.

They didn’t design a language that millions of human engineers enjoy (?, lol) using. They took an existing codebase and ported it. Yes, the porting part is easier now but only because another project and spec exist.

If it’s so easy, then please ask it to make the globe stop glitching out and flashing on scroll.

> What will you do if

He will ask Claude.

Where’s the ambition? This reads like a long ad for Claude, from an EM with AI psychosis.

> I want a deeper version of this task, not a bigger one. Before rewriting it: (1) say what a top professional in this field would do here that I’m not asking for; (2) name the rawest material they would start from instead of what has already been digested for me; (3) name the specific methods and tools they would use; (4) say what, other than you or me, would show the result is right. Then rewrite my prompt to ask for exactly that.

Sorry, but this is along the same vein as “make no mistakes”. Don’t give Anthropic even more of your money to burn tokens on stuff like this.

> This isn’t a particularly unique insight, every single heist movie spends the first 30 minutes assembling a diverse cast of characters and talents. As AI products make it easier and easier to run multi-agent systems (with multiple threads, orchestrators, or simply subagents), I’ve seen really interesting results by imploring Claude to bring in additional fields.

Again, this is an ad to get you to burn more tokens.

> Meetings (the good kind, anyway) ideally end with some decisions. Ask Claude: “Work out which three decisions are most urgent in the face of everything you’ve learned, and start working on potential directions with for/against arguments.”

Jesus, man, weren’t you just in the meeting? Just send your Claude next time, please don’t bother attending. This isn’t even ambition, it’s laziness.

—-

Use AI all you want: let it unblock you and move on to the next thing.

Anthropic employees just need to practice being normal human beings. Outside of their cult, the stuff they say is just weird.

Great idea, bookmarked. Thanks for building this.

Yay, all software will be open…Except the models.

It’s not the ability to find jobs. It’s the ratio of pay to value delivered.

Nearly every app or website I use today is broken, slow or hostile to the user. Show me the value for the pay.

> whose labor does not produce >= $minimum_wage worth of value

Same thing we’ve been doing for other fields like software engineers - just pay them more.

> just as nobody wants to type opcodes, or write their own http clients

This is how you get faster software. You literally look “into” the code, see why stuff is slow, remove the extra work in the library that you do not need, and now your software has a faster server.

If you think software performance is a solved problem today, there is nothing more I have to say.

Consumer software is slower than ever. And only getting worse.

There are plenty of people who understand the stack and ship actually fast software. This might be a skill issue that you’re choosing to frame as a “best practice”, because you do not want to put in the work.

Our end users are who should benefit. You’re the pilot in the seat who doesn’t know what the throttle is and you’re telling the passenger it’s the plane’s fault it’s slow.

Abstractions are convenience. They’re not free, there is a cost to any work you ask the computer to do. Just staying at the surface level and never understanding what’s under the top level is why software is slow and bloated today. You’re supposed to move beyond the abstraction, understand what you need underneath and use what you really want to do the task.

No wonder we boot up entire browser engines to write simple text editors. But hey, we gotta be first to market to get that VC money, right?

No mention for them training on what we create (without our permission), just to sell it back to us?

Absolutely. tooling is very rest of the owl when it comes to building something rather than just working with debug data.

I’m certain there’s enough actual game engine code in the datasets that with enough token spend, you could have a platform layer, basic renderer, entities moving around.

There would be absolutely no point in creating one over using one that exists and since there’s no learning that’ll come of it, it’s kinda wasting money.

Unless you’ve written one before, it’s the natural learning curve.

You can always generate one using LLM if you don’t care about how it actually works.

> Because these AI companies rent a lot of GPU to render the UI

What AI company is rendering websites for me on their GPUs?

> We’ll start seeing more optimized code.

No. We'll see more AI-generated code. AI-generated code is derived from human generated code. Most human generated code is slow (see: your own title).