I am a King, but local 😂
Summary
A user jokes about feeling like a 'local King' running two Strata engines at 70 tps and 12M tokens daily, contrasting it with Poteto, a former Cursor employee now at xAI, who reportedly uses 34M tokens per minute and ships 2,500 PRs a month to Cursor and GrokBot.
Similar Articles
@leerob: I thought the growth of Cursor was insane, but Grok @Bot is blowing me away. This feels like something special. Will be…
The tweet expresses amazement at the rapid growth of Grok @Bot compared to Cursor and mentions plans to train Grok 4.7 for better performance in the Bot harness.
@aehyok: Grok Bot's true unlimited token 2.0 version is here. Real 24*7 hour operation—as long as you have a graphics card, you …
Grok Bot's 'unlimited token 2.0' trick is shared, showing how to connect Grok Bot to a local model via Tailscale so it can run 24/7 on your own graphics card for effectively unlimited tokens.
@0xMorlex: Former Cursor engineer, now building agents in Grok 4.6: He’s already running → 10 GrokBot agents across his: inbox, re…
A deep dive into a former Cursor engineer's use of 10 GrokBot agents built on Grok 4.6 to automate tasks like inbox, research, and operations, showcasing the future of specialized AI agent stacks.
@lxfater: Local inference 125b large model, 3 times your sol return speed IQ exceeds Claude Opus 4.6 Max From now on, tokens flow…
A tweet claims a 125B-parameter model can run with local inference at up to 3x faster speed than a reference point, with performance said to exceed Claude Opus 4.6 Max, suggesting abundant locally available tokens.
@sama: https://x.com/sama/status/2075047983314571764
Sam Altman highlights a user's praise for GPT-5.6, emphasizing its reliability and fun use, which led to a 5x increase in token usage on their team.