sejje

Bring in the bots.

I'd make him use Claude Code

https://serper.dev/ is $1 per 1,000

They have 2,500 free which I used, it seemed good.

I'm unaffiliated--actually a clanker told me about it so I told it "go ahead"

No offense, I wouldn't defer to you to make my arguments. Thanks for the advice, though.

Why would that serve the author?

What were his metrics?

No it's not.

Either the stuff is worth reading, or it's not worth reading. It really has nothing to do with how much effort it took the human, or entity, to get it on paper.

Gold that lands in my pocket is just as good as, or better than, gold I have to dig out of the ground.

It's not low-effort just because you didn't read the code. Used to be, not anymore.

The game can have every detail tended to by a game designer, while the clanker builds it out.

Well, my project IS complete, although I keep adding new stuff--it's going to be that kind of app, it rotates content in (minigames).

It has about 8 minigames, leaderboards, awards, achievements, async image generation, inventory, inventory-interaction-with-minigames, and various other account features, mailers, notifications, blah blah.

Literally haven't had one issue with context or micro-managing the agents on this project, iirc. I built it in a couple weeks.

Minigames are like "putt putt golf w/ daily generated levels", "slot machine," "video poker", etc. Not like "tap the fastest" or something with no complexity.

I got >$100 of value in about 2 minutes of effort yesterday.

I typed a design I wanted, it built it. 2 minutes of my own time, 1% of my weekly limit.

I actually think the design would have cost 4-6k for an equivalent thing by a human, and would have had them laboring for a couple weeks.

some/most of that could easily be optimized for: set expectations for turn-time ahead of time, and it will meet them. if you had even just given it a clock to pay attention to, it would have noticed on its own, i reckon.

i'm not having problems yet in my biggest ai-only codebase, which is over 100k lines now. i haven't had any model hiccup, actually, but the smaller models take more wall time to get it done.

i have the models writing in rust, i believe it helps. ymmv.

i don't think it always architects well or anything, but it has quit building broken shit. it gets lazy, builds dumb UI, puts way too much text everywhere--but only if i don't remember to give it some better guidelines, or a visual reference.

i think with the right context, they build the right thing, and we haven't totally solved that just yet. but close enough for me; i'm so thrilled. i just want opus 5.5 to be crazy fast, like chatjimmy.

Not him, but I'll answer: me! I'm building software for my (non-software) business.

> why should I spend my time reading an article the "author" couldn't even spend their own time writing?

The same reasons you might spend your cycles running code the "author" couldn't even spend their own time writing.

i'll be deleting code for a couple of model generations. the new, better model will delete bad old code written by older models.

and then, at some point, that will cease to be able to happen. they'll be good enough.

i predict that happens before March 2027.

How fast can you get it into the repo, tested, deployed?

How fast can you scaffold new ideas and delete them when they don't work?

You're still allowed to do that, even if you don't want to write the glue code.

they can just use the user ip. i think grok already does this.

> I'm curious to see what you can do on an 8GB consumer GPU these days.

Nothing, really. Might be coming soon, but no.

You probably want to try bonsai, I guess, but don't expect good results.

Sure, that's a random commenter.

I meant a company making an opposing claim, or the government perhaps.

There can also be two or more models involved.

Do they have a caps lock waiting to be remapped?

Well, because there's a chatbot powering america.gov, and there's only a few choices for models/companies--of which grok is one. And here Musk is claiming grok was chosen, while nobody else seems to be making an opposing claim.

Hundreds of illegal voters that were already caught, exactly.

While everyone says that's not happening.

Over 6,000 illegals registered to vote in a couple of years, and 400 of them actually voted. So not a handful, try reading comprehension.

Yes, people are saying "Trump is trying to stay in power"

That's my best guess at what you're refuting, since I had it in quotes. Otherwise you're just vagueposting on a 4-day old thread. Try being more specific, make a point.

Come and take it.

> Humans should be handling design and implementation entirely, making things for other humans. An LLM running in a loop can't build humane systems.

I tell the LLM what to do in its loop. It builds it. I tweak it until it is perfect. I care a lot about UI.

I'm mostly building my own UIs lately, but I find no problem with the development loop. I'm building much better UIs, because it's way easier to test things, and scrap things that I thought would work, but don't. It all happens in a matter of minutes.

Humans should use more llms.

So vibecoded, but with last year's models.

That figures, government moves slow.

How about semantic embeddings for everything to facilitate search, and then don't let a bot spam sycophantic shit at me?

I'm very pro-ai, but we can improve the UI a lot sometimes, from the chat bot paradigm.

Do you not think we can take that at face value?

Why not?

I just didn't believe him, actually.

A neighboring warehouse/supply place has an old system of some kind, I think DOS.

Old monochrome screens, and one of those printers you can hear ripping off every line, and it has the perforated sides for feeding that you rip off.

I haven't been over there in a while, but someone brought me back a receipt yesterday and it was printed like a modern invoice. I guess they updated.

Did you type the translation? It has a typo.

Can I introduce you to copy and paste?