More posts
. I've been on it almost a week and still nothing. Anyone actually managed to get in?
I upgraded to Google's top AI tier and I'm not mad about it. Two prices: $99.99 for 5x usage, $199.99 for 20x. Both come with monthly Cloud credits, $40 or $100, which you can burn on Gemini API calls. The $300 credit for new accounts is one and done, but Ultra's keep arriving, and they cover third party models too, Claude, Grok, DeepSeek, Kimi. Twelve months of that and the plan costs about half what you're paying. The Gemini app has 4 Argon plus Gemini Spark, an agent that just stays on between your messages. Flow hands you 10,000 to 25,000 credits, enough video generation that I stopped counting. Flow Music is 30,000 credits a month, around 6,000 songs, commercial use included. Antigravity runs 4 Argon and the weekly quota doesn't bottleneck me. Only thing I hate is the 5 hour refresh window. Standard Google stuff comes with it too: 20 to 30 TB of storage, YouTube Premium, Home Premium Advanced, an AI coach in Google Health.
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.
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.
