browser automation, this is the agent i'd recommend.

2026-11-12 07:27

browser automation, this is the agent i'd recommend. hark personal agent. posted about it a while back, then let it sit unused. recently moved some tasks from muse over to hark. did not expect it to be this good. example: auto-listing a virtual product, then auto-withdrawing the payout. muse's browser automation froze mid-run. gemini spark refused the withdrawal, blocked by its own safety settings. cue refused the login, same story. only hark did it stable and smooth. same with content distribution on chinese platforms. hark does all of it by simulating real human clicks in the browser. heard hark runs on opus-5.5 under the hood. sure enough, when the model is smart enough, harness design just stops mattering that much.

OpenAI really does police everything.

Ran a reverse engineering job on rea with gpt-6-astra. It kept refusing me, and after I spam "continue" a few times, I got an email warning that my account would be deactivated. For a company called Open, they're not very open. The actually open one is deepseek. I don't think their official API has ever refused me once.

2026-11-12

My Claude didn't last a week.

If the appeal doesn't unban me, I'm done. Days of this, I'm tired. IP, language, timezone, subscription region all match. Even the timezone Claude reads in chat is my environment's. Suspects: new account, Microsoft email, fable-5.2 eating the 5h quota in ten-odd minutes and not being worth it.

2026-11-12

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