We’re rolling out monthly Claude Platform API credits for Max and Team plans:
Max 5x: $100
Max 20x: $200
Team: up to $500, pooled
Works on any model, including Haiku 5.5, in your code or third-party harnesses.
How it works and full terms: support.claude.com/en/articl…
Bootstrapping PirateFace with a seedbox.
If you need a referral on where to grab a seedbox, or how to use one, let me know in the comments.
I'm banking points & backing up obliterated models.
👇
I might take this down since I’m currently using deepseek and with the high lead of deepseek I feel like we’re introducing things to the bench that it’s already gonna win at not even based on performance
got 4 rate limits and like an hour out of 8 bots trying to "make me a millionaire" this is on the Pro plan so its expected. since i have a claude sub i cant wait for them to have their own bot!
SITUATION DETECTED: opencode is using an AI “pricing engine” to analyze millions of daily sessions across 100 Trillion tokens, estimate each persons willingness to pay, and then generate what it calls “the optimal price” for every model for all users, per Reuters.
Oh yeah, fine dude even though sols running at a fourth of the fucking advertised speed let’s have a reset tomorrow. Everyone get a reset reset reset
I just want it to fucking work
oh fuck i was fine with the baby benches 😅
The real pull-request benchmark is built and running: 11 real merged pull requests from errand, jgengine and *****
Sizes: four small fixes, five medium features, and two large changes across 11–18 files.
One Quest Giver model request hung for 175 s, for just 269 tokens of output. That's the provider being slow for Sol 6, not our code. waste my eval
🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬🤬