Comment by pimeys
6 hours ago
Yes. You have to find the provider with pricing that suits your usage.
I am having 98% my input in cache, so using Coralbricks makes sense due to them giving cache reads for free — you only pay for writes. I spend maybe 5-10 dollars a day and my agents basically work day and night implementing things for me.
If your tasks are write-heavy, find a provider with cheaper output.
If you build a customer-facing app, pay a bit extra for 400+ tok/s e.g. on Lithos.
What are your agents implementing day and night…sheesh. Built anything useful for anyone yet?
>What are your agents implementing day and night…sheesh. Built anything useful for anyone yet?
you can't think of anything to unleash some agents on within the entire digital world at any given time?
you motivate your own personal work only via gauging its' usefulness to others and your own prospects?
sheesh.
built anything for the sake of building yet?
“building for the sake of building” refers to _you_ doing the building
6 replies →
>you can't think of anything to unleash some agents on within the entire digital world at any given time?
It has to be worth it though right? Like I could spend some money and have agents build me my own Photoshop maybe (maybe?) But it would definitely be much worse to use than actual Photoshop. Then I have to have the continued interest to keep improving it which probably won't happen because the next shiny thing will grab my attention. So it all just seems like a bunch of kids that have been given a seemingly endless supply of free candy and they are going fucking nuts like chipmunks with ADHD on crack. Building all this shit that is absolutely meaningless. I realize I've gone on a rant but I'll keep going. I strongly suspect (with no evidence whatsoever) that the people who are churning slop apps out at breakneck speed have never been to an art museum. There. I said it. You've all got no taste. You wouldn't know a quality product if it hit you in the face. I'll leave with this thought- if apple didn't exist, would they ever exist now we have LLMs? I say no, because the age of good taste and refined design and original thoughts is gone forever now that we have Claude and chatgpt and agents.
2 replies →
[flagged]
Sheesh... what's in a name? :p
Bio shows: https://twin.so/
That promo video … it’s so cringe it feels like satire. But it’s not.
It’s PERFECT!
Codes day and night a snake eating its own tail…
2 replies →
I tried fireworks.ai, drawn in by their supposed blazing speed. Yawn. Mostly worse than vanilla Deepseek.
Is Lithos actually fast for common usage?
You have all the struggles for the price of Anthropic / cursor subscription. I use the first one I code large chunks some PR are 50k LOC and I have at least 2-3 like this a week . It’s a greenfield project .
I still have quotas left I use it for home things build 3d model of my renovation projects, alerts for shopping list etc . And yeah I use cutting edge of cutting edge of models that saves me time and money , only discount monitor saved me ~$2k on my renovation project
Why the hell would you put 50k lines into a single PR?
I mean, why even pretend you’re going to “review” something that large? Just build everything on main.
PR is just an entity to review /do some other LLM processes . Human part check other models review PR's, tests all kind of , security etc. Also human is to checks docs, specs in the pr, db migrations if any , some of the tests related to the PR. We stopped reading the code after opus 4.6. Sometimes for very core parts i skim through files just to make sure if the changes were correct.
1 reply →
I agree. I code a lot, a lot! And maybe my code is shitty, but yeah, I burn a lot of tokens, and I couldn’t do it without Chinese models. I’m just a random dev in the middle of nowhere. And I don’t feel like I’m missing out on anything with my setup at all.