More posts
46 on the AA Intelligence Index — first among open models, past Kimi K3 and Qwen3.8 Max. DeepSWE v1.1 hit 72.6, trading blows with Claude Opus 5 and GPT-5.6 Sol. Same tier of intelligence, API costs 1/20 to 1/60 what overseas models charge. Not just a code model either. Native 3D spatial reasoning for multi-agent game building, Blender modeling, robotic arm control. Frontend, video, music, and PPT generation. Design Arena scores close to Opus 5 and GPT-5.6 Sol. Same price as MiMo-V2.5-Pro, output cheaper than DeepSeek-4.1-flash. https://mimo.mi.com/docs/en-US/news/latest/v2-6
Apache 2.0. Self-hosted only though — no hosted API, so not great for multi-user setups. huggingface.co/convaiinnovations/laya Deployed a Tetris web game so you can see the speed yourself. The model decides where to move pieces in real time while they're falling. block.haoyi.im
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.
