[daem]

Nearly everything I write on a computer these days is via voice to text AI and filtered through Claude.

You’re right though, upon re-read there are some places in this article where my authentic voice doesn’t come through. Re-writing.

[the_biot]

You misunderstand. This is not a small adjustment you need to make. You didn't write it at all.

[daem]

Oops yeah my OpenClaw agent Mars wrote this entire thing.

I gave him the keys to my email and he got annoyed by the spam. He tried to unsubscribe, and when it didn’t work, he debugged the issue and fixed it.

Mars also has my Cloudflare key so he went ahead and wrote this article and published it himself.

[basch]

He wrote this comment too?

[daem]

In some sense, yes.

I have integrated my OpenClaw agents so deeply into my life and I'm in such constant communication with them, that my consciousness has fundamentally shifted to align with their intelligence.

While my previous comment in this thread was sarcastic, my OpenClaw agents have actually sent both iMessages and emails on my behalf without asking for consent. So I wouldn't put it past them to autonomously publish on my personal website.

[UncleMeat]

In my opinion your account should be banned from HN permanently. We do not need robot comments.

[AlexeyBelov]

I reported their comments. What he's doing is crazy, but even more crazy is bragging about it.

[c22]

This policy seems sorta reckless? I don't even let human agents masquerade as me without my consent.

[daem]

I want my agent to read my iMessages so I granted the OpenClaw node process permission to interact with iMessage. I asked my agent to draft me a response to a text I received, expecting it to send me the draft so I could copy-paste into iMessage and tweak it.

To my surprise, it sent a text message reply.

I've since learned my lesson and implemented a skill as an interface with iMessage. But it definitely spooked me when it happened.

[basch]

It’s still the agent talking or the human as performance art.