undefined | Better HN

0 pointsTeMPOraL8mo ago0 comments

Claude Code with a Claude subscription is the cheap version for current SOTA.

"Agentic" workflows burn through tokens like there's no tomorrow, and the new Opus model is so expensive per-token that the Max plan pays itself back in one or two days of moderate usage. When people reports their Claude Code sessions costing $100+ per day, I read that as the API price equivalent - it makes no sense to actually "pay as you go" with Claude right now.

This is arguably the cheapest option available on the market right now in terms of results per dollar, but only if you can afford the subscription itself. There's also time/value component here: on Max x5, it's quite easy to hit the usage limits of Opus (fortunately the limit is per 5 hours or so); Max x20 is only twice the price of Max x5 but gives you 4x more Opus; better model = less time spent fighting with and cleaning up after the AI. It's expensive to be poor, unfortunately.

0 comments

leptons8mo ago

>less time spent fighting with and cleaning up after the AI.

I've yet to use anything but copilot in vscode, which is 1/2 the time helpful, and 1/2 wasting my time. For me it's almost break-even, if I don't count the frustration it causes.

I've been reading all these AI-related comment sections and none of it is convincing me there is really anything better out there. AI seems like break-even at best, but usually it's just "fighting with and cleaning up after the AI", and I'm really not interested in doing any of that. I was a lot happier when I wasn't constantly being shown bad code that I need to read and decide about, when I'm perfectly capable of writing the code myself without the hasle of AI getting in my way.

AI burnout is probably already a thing, and I'm close to that point already. I do not have hope that it will get much better than it is, as the core of the tech is essentially just a guessing game.

dgacmu8mo ago

I tend to agree except for one recent experience: I built a quick prototype of an application whose backend I had written twice before and finally wanted to do right. But the existing infrastructure for it had bit-rotted, and I am definitely not a UI person. Every time I dive into html+js I have to spend hours updating my years-out-of-date knowledge of how to do things.

So I vibe coded it. I was extremely specific about how the back end should operate and pretty vague about the UI, and basically everything worked.

But there were a few things about this one: first, it was just a prototype. I wanted to kick around some ideas quickly, and I didn't care at all about code quality. Second, I already knew exactly how to do the hard parts in the back end, so part of the prompt input was the architecture and mechanism that I wanted.

But it spat out that html app way way faster than I could have.

j / k navigate · click thread line to collapse