Hermes Agent's mobile app is waitlist-only now
More posts
Switched my daily driver to gpt-6.1-terra.
The whole world finally went quiet. I'd been on the official deepseek-v4.1-flash and it just would not shut up. Verbose, over-thought everything, fired tokens out fast, then crawled to the actual result. DS scored 33 on the AA benchmark (33% task success). At $0.6 a run that's ~3 attempts per finished task, so $1.8 each. Terra (high) scores 42.4 at $0.26 a run. ~2.5 attempts per success, $0.65 each. So the model that looks more expensive is cheaper per real result. With GPT Pro 200, Terra chews through ~10B tokens a week for me (YMMV), and that $200/mo covers one person's whole usage. Model picker: haoyi.im/models

Perplexity just launched Teammates, AI colleagues that don't
clock out. They plan projects, watch your Slack/GitHub/Gmail, follow up without being asked, and hand tasks to other Teammates when something's out of their lane. Each runs in its own sandbox with encrypted creds, and you can grab the wheel anytime. Max-only for now, live on the web.

My agent now pushes to 19 platforms by itself.
Letting Muse run the whole thing is genuinely nice, the only snag being the Chinese platforms won't auto-post, probably because Muse's browser automation is just weak. Used to take me an hour or two to cover all 19. So I built my own publish endpoint: I post on my site once and it syncs everywhere.

Free 4-core / 8GB cloud box, go grab one
Simular Box is popping up everywhere this week. It hands your agent a cloud computer that just sleeps when it's not being used. Under the hood it's a cloud Ubuntu desktop. Folks who've poked at it are seeing ~4 cores, 8GB RAM, 40GB disk, plus sudo. Wire up any agent and it gets its own browser, terminal, and desktop: it can browse, click, run code, all isolated from your real machine. Feels a bit like what Muse is doing. Free tier exists: a daily credit allowance that resets every day and doesn't carry over. 🔗 box.simular.ai
