9router now routes decision models too. Set one up on the system-one page and it goes through 9router like everything else, one place to manage and call it.
9router now routes decision models too
More posts
Google just opened up Gemini's "Call for Me." The AI dials
businesses using your number, tells them it's "Google's AI assistant, calling on your behalf," and handles the actual errand: check a menu, book a table, move an appointment. Live transcript the whole time, and you can hit Take over whenever you want the phone back. It won't dial 911, take a payment, or read out your SSN or password. Limits: US only, Pixel 11 only, paid Gemini plan plus the Phone beta, and a daily cap on calls.
Claude Opus 5.5 is out. First model in the 5.5 lineup.
Anthropic says it hits Fable 5.1 on most tasks, runs about 40% cheaper than Opus 5, and streams more than 30% faster. Price is $4 / $20 per million tokens. Opus 5 was $5 / $25. Cache reads dropped from $0.50 to $0.20. Terminal-Bench 4.0: 66.4%. CursorBench: 57.8%. Both ahead of Fable 5.1. Pro, Max, and Team get a higher five-hour cap. Sonnet 5.5 and Haiku 5.5 are supposed to land in the next few weeks.
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.
