Grok quietly gave everyone a weekly quota reset. Go use it.
Grok quietly gave everyone a weekly quota reset. Go use it.
More posts
Tried the same prompt on the latest models: Grok-4.6
, DS-V4-Pro-0813, GLM-5.3, Gemini-3.7-Flash Prompt: make a baseball web game, bilingual Chinese + English GLM-5.3 had the best frontend. Grok-4.6 was the most complete overall — batting, pitching, strike zones, balls, strikes, whiffs, base running, plus two field skins (dirt field and night game) DS-V4-Pro-0813: batting, balls, strikes, whiffs, but no base running GLM-5.3: batting, balls, strikes, whiffs, with base running Gemini-3.7-Flash: batting, balls, strikes, no whiffs, with base running
Ran Qwen3.8-27B-4bit locally on my M1 Pro 32GB
. 10 tok/s. Each sentence hangs for 2-3 seconds before output starts. Long prompt prefill takes over a minute. 128K context, in theory. 27B boots up fine on M1 Pro, but as a daily driver it falls short. Need double the memory bandwidth to hit 20 tok/s for a smooth experience.
Claude appeal rejected.
Won't refund the subscription either. I'm half convinced the appeal email is itself phishing, because I'm pretty sure they log the IP. DHH came to Shenzhen recently and showed how he uses Claude Code over there. That's the safest way now, honestly: run Claude Code on an overseas machine, connect through Tailscale, never use it locally. So I need to rent an overseas box with a residential IP, and register and log into Claude there.
Sharing my current mobile only workflow.
Until late September it was the usual setup: parked in front of my laptop, terminal open, bossing pi around, fanning out subagents, then eyeballing diffs myself and filing the PR. Glued to the chair all day, every day. Late September I moved the whole thing to my phone, Hermes runs the show, pi takes the orders. My back is very grateful. Three weeks in, still no regrets. Stack: Hermes on flagship brains (gpt-6-astra / opus-5.5), pi on mid-tier (ds-v4.1-flash / sonnet / terra) with as few plugins as possible, the two talking over a2a. Hermes reads the issues, slices them into small tasks, spins up a worktree for each one, and dispatches a pi into it. When a pi finishes it pings Hermes, who decides: ship the PR or bounce it back for rework. I get back from a full day of being a tourist, or just wake up, and a dozen PRs are sitting there done. Pretty sweet. The catch is how black-box the whole thing is. My emotional arc has been a rerun of early vibe coding, except back then I at least read the diffs. Now even that goes to a flagship model. Boxes all the way down. If you don't have data anxiety, grok-bot and chatgpt-dot basically ship this out of the box, grok-cli and codex built in, native agent-to-agent comms. Downside: your code lives on their servers, everything's moderated, and one ban takes it all with it.
