I used my $200 free fable 5.1 credits to build a WhatsApp sticker maker, it created a version I was not happy with, but it burned the 200 in one sitting. Node.js app, vue frontend, etc.

I didn't used the project a lot since I kind of hate it on how much was spend.

Last week I used just a little bit of my $20 pro account to build a replacement with rust end to end, just to gain some experience with the rust hype. Very happy with the result, not perfect but snappier, and even better: a single executable, I no longer need to fire up a backend and front service separately.

What model did you use for the rust rewrite? Opus 5.5? I mean it seems pretty crazy that you had such different results.

Yes, Opus 5.5 with high effort for planning. Audit the plan with another Opus session, fix inconsistencies. Then implement with Sonnet 5.5.

I use Sonnet 5.5 and Opus 5.5 both on Medium to produce apps in Rust/Tauri all day every day on a $20 Pro sub, and absolutely these two models do a great job with that stack. I rarely run out of weekly credits, unless I use Opus 5.5 on high or ultra code. Medium does the job 99% of the time. Fable is good, but it'll never be as good as Opus when well prompted and with some iteration. I see Fable as a preview of what the next model will be able to do, but it's really not a good production model unless you have a lot of cash to burn.

I am not convinced with Fable capabilities. I think Fable is for lazy people with a lot of money, but still, a skill-able person can out run fable with the $20 pro account.

Google's Argon model via antigravity is unusable, for a small code review I asked, already spent like 10% of the weekly usage, in less than 10 mins. Very useless imho.

I always find DS or Qwen to be very spot on on audit changes or plans for just a few cents.

I'm baffled, my $20 is enough for me to do some consulting, personal projects and side work, and still cannot outran my quotas, I'm building different kind of things: flutter apps, dotnet backend, database, front end, architecture diagrams, code exploration, tests, PowerShell scripts.

How people spend more than 200 usd monthly is beyond my understanding, are you guys so inefficient with the usage? or I am the opposite?

Without any context for what you're working on, I'd have to assume the reason you don't hit the $20 subscription limit is that you're either not using it very often, or you're working on some relatively basic CRUD app that doesn't require it to think very deeply.

I tear through my $200 subscription because I often have 3-4 agents running simultaneously, exploring performance optimizations, building features, monitoring production rollouts, or investigating production problems/customer issues in parallel.

The downside is that I do spend most of my time reading the agent's output these days.

I think I do quite the same as you, complex features, not anything basic.

Well, it works for you.

I think this is the clearest example of: exceptions don't make the rules.

Author might be a vibe coder, designer or someone who does not do really heavy and complicated development, maybe some api here and there.

But it is pretty obvious that a very concerned engineer would not allow any of that, for critical systems.

This is an out of touch with reality thing to say. Remember: not everyone has access to unlimited usage/money to spend tokens or the most expensive models with the higher thinking settings, exceptions does not make the rules.

> This is an out of touch with reality thing to say

I mean, you're discussing this with a marketer/someone wearing a marketing hat, who works for a company which needs people to use as many tokens a possible. That's their reality

Thanks Stephen for this, it is very rewarding to read something very technical that is not AI slop these days.