Post

I am against whatever the fuck this is dude. I just think this is bad lol.

not only is this kind of obviously an abusive of the plans, this just seems like you have a serious problem lmao.

0 reposts60 likes

this is like 10k effective API token spend???? to make a couple chat apps? genuinely what are you doing here

he has exactly 3 projects, t3 chat, t3 code, and a web app template?

And it's more like 100k spend. Fable 5.1 is expensive and Theo used to use it for everything.

Really depends. Up until Opus 5.5 he kept insisting in using Fable and Astra for everything. From my experience what's driving up my costs are adversarial reviews. Some PRs go for 7 or 8 rounds before a signoff. Agents (Opus+) keep saying the findings are legit so it's hard to cut them short.

Yup exactly this. At work, we have a skill that spins up an adversarial review with a few models and they build consensus. That *EATS* tokens.

don’t plans give you like 5k per month in api costs? assuming he is talking about claude

I think estimates tend to vary, I was assuming about 2k if you were really pushing it aggressively.

oh interesting. i remember a few months back everyone was sharing the numbers and i feel like people were showing roughly 5k in tokens. i mean idfk what he is doing either way, but would be way more atrocious if it was 25-30k in spend lol

it varies by model i think, i had a few rogue sonnet 5 agents run thousands of "echo waiting" calls in an unattended workflow and the session came out to $2300 but only ate a third of my 20x weekly usage

he does the same thing over and over again. he has projects that he’s gotten to “90%” 3+ times and just redoes the same projects when the new models come out. i listen to theo when it comes to model comparisons, but not on how to be a productive engineer