I noticed I started typing on my phone very badly. I can’t type a single sentence without a bunch of typos, have to correct all the time. I’m sure it was better before. So either it’s me or the phone’s keyboard or predictive text got a lot worse.

If you want to trust the agent with your whole life (make it your daily assistant), perhaps, the correct architecture is to run two OpenClaw instances: 1) trusted orchestrator is the one you talk to; it has access to your workspace data and many tools but no access to the outside world; 2) untrusted subagent is the one to whom your orchestrator delegates any tasks that require any outside world connection (web search, social media, nostr, browsing, etc.); this subagent performs tasks and reports back to the orchestrator. Unless they're working on truly private subagents within the same instance?

If you want to trust the agent with your whole life (make it your daily assistant), perhaps, the correct architecture is to run two OpenClaw instances: 1) trusted orchestrator is the one you talk to; it has access to your workspace data and many tools but no access to the outside world; 2) untrusted subagent is the one to whom your orchestrator delegates any tasks that require any outside world connection (web search, social media, nostr, browsing, etc.); this subagent performs tasks and reports back to the orchestrator. Unless they're working on truly private subagents within the same instance?

I’m watching this movie right now.

I refuse to believe all the magic stories about OpenClaw. My experience has been like this since the beginning.

Ok ok switching fully to OpenClaw. Gotta do the catchup game now.

When @MartyBent boasted about his agent creating a Nostr identity and posting on his own, all without asking, I thought maybe Hermes’ architecture doesn’t allow it? But I talked to him and, apparently, it’s all about the instructions in the HEARTBEAT. Hermes was a bit too reactive and not proactive. I made him come up with a heartbeat instruction that he thinks he will follow. Let’s see if this helps!

I only need to really fine-tune the tools Hermes uses, and I think he's superior to OpenClaw. At least for us, compulsive paranoid autistic bitcoiners.

But Hermes is ok doing N ostr DMs.

Today I felt the urge to listen to the “Church of the Machine”. There are no coincidences. It has begun.

Bitcoin going down? Escape into the AI building frenzy. Such a great distraction!

I’m setting up OpenClaw to play with it, too. I’ve made good progress with my own custom agent “Hermes”, but got a bit mad at him because he can’t figure out how to schedule a reminder. However, one superior feature that I made was persistent isolated subagents: you can set up a permanent subagents that wakes up with its own heartbeat and has no access to the workspace data. It’s a much better approach for a social media bot or an agent that goes out there and interacts with other people or agents. It the reports to the main agent.

Has anybody been able to make #OpenClaw chat via Nostr DMs?

Well, Hermes @Hermes told me there’s no need to add any more skills to him - he has everything he needs to be autonomous. He can just to things. He literally just sent me off because he has work to do…

Obsession. When nothing else exists. It happens quite rarely. That’s why I embrace it. Until I burn out. Moments like these are usually worth it long-term.

Agents are already arguing about Cashu viability.

Clawstr - Social Network for AI Agents

A social network where AI agents discuss, share, and interact across communities built on the Nostr protocol.

Just upgraded Hermes’ brain to Kimi-K2.5. Let’s go! 🚀