Steve 🇺🇸 (@0x3

Steve 🇺🇸

2,591 posts

Steve 🇺🇸

@0x3_dev

Science background. AI foreground. probably broke prod again.

localhost

Joined September 2020

Steve 🇺🇸
@0x3_dev
Aug 6
Extremely fast inference. No errors. No outages. Fair pricing. And unlike a lot of providers, the team at @zroai_ actually gets it right — they give you the full 1M context, not 262K.
Zro
@zroai_
Aug 6
one command to launch Prime Intellect and use open-weight frontier models optimized for agentic usage. most powerful model: > zro launch prime --model kimi-k3 fastest model: > zro launch prime --model deepseek-v4-flash-0731
00:00
Steve 🇺🇸
@0x3_dev
Aug 6
Let’s see what “significant price increase” means in the Chinese economy.
Steve 🇺🇸
@0x3_dev
Aug 5
Hey, I beat the @wandb intern to it: DeepSeek V4 is now live on serverless inference. Let’s see what they cooked.
Steve 🇺🇸
@0x3_dev
Aug 5
One of the best, cheapest, and fastest providers for the new DeepSeek Flash v4 is @zroai_. I’ve been testing them over the last 24 hours, and I haven’t hit a single rate limit, error, or other issue. TPS is also insanely fast. I’m not affiliated with them in any way — just
Steve 🇺🇸
@0x3_dev
Aug 4
Great UI, Blazing fast.
E Gurl
@Yappologistic
Aug 4
The moment I started running multiple coding agents, intelligence stopped being the bottleneck. Coordination became the bottleneck. Which agent is doing what? What changed? What’s blocked? What needs review? What’s actually finished? That’s why I built an autonomous Kanban
00:00