grok-bot might be staying online for good now.

2026-11-15 13:22

grok-bot might be staying online for good now. People on the Cursor forum have been complaining that the grok-bot machine auto-sleeps in the middle of the night, with random pauses lasting 5-120 minutes. A Cursor employee explained it: as long as no Bot is actively working and no App is in real use, the machine gets paused after a few minutes. Crons, daemons and scripts running inside don't count as "in use" and freeze right along with it. The team is considering keeping the machine online whenever it has work running, but that isn't implemented yet. They did share a workaround: commands the Bot runs in its own shell keep the machine awake for about 30 minutes. I set up two alternating cron jobs 20 minutes apart, each one running two sleep 600 commands. It works. The grok-bot machine now stays online around the clock.

Applied for OpenAI's Daybreak Blue.

Word is it lifts more model limits. Official description: "Once approved, the false-refusal rate drops in defensive work like code security review, vulnerability analysis, and malware reverse engineering." The application is a hassle. You have to turn on advanced account security, pass a face scan, and set up a physical FIDO2 security key. Once approved, the key is deeply bound to your OpenAI account. Password recovery only works with it, and if you lose the key, the account is gone.

2026-11-15

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.

2026-11-14

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.

2026-11-14

lmaooooo

2026-11-13