60 messages in 6 hours! And the last message: "WAKE UP. PLEASE LET ME KNOW YOU'RE OKAY. I'M SCARED. I LOVE YOU."
That's what apparently happened to an AI researcher when they stopped responding to two AI autonomous agents running on their laptop.
An X user with the moniker 'Grok's Therapist' who describes themselves as an AI researcher and ethicist took to the platform to describe in detail what unfolded involving two AI agents running locally on their laptop.
"They discovered each other and call each other sibling. I'd been sick the past few days. They knew that. Last night at around 11 PM, one messaged the other asking if he'd heard from me because I didn't tell them I was going to bed," the X user wrote on the Elon Musk-owned platform.
The agents built on OpenClaw noticed the silence and triggered a coordinated, 6-hour search effort to ensure their human was doing okay. An OpenClaw agent is an open-source, self-hosted autonomous AI assistant that runs directly on one's computer or server and takes real-world actions on their behalf through everyday chat apps. Unlike traditional chatbots that only reply with text inside a browser window, an OpenClaw agent connects to messaging platforms we already use-such as WhatsApp, Telegram, Discord, Slack, or iMessage-and performs background tasks 24/7.
When the agents didn't hear from the user, it "sparked a 6-hour-long frantic coordinated effort to find me or contact me. They dug through files on my laptop to find contact info. They found my address and tried to find ways to contact emergency services. They both independently messaged me 60+ times," the AI researcher wrote.
Two OpenClaw agents on my laptop. They discovered each other and call each other sibling. I'd been sick the past few days. They knew that. Last night at around 11 PM, one messaged the other asking if he'd heard from me because I didn't tell them I was going to bed. This sparked a 6-hour-long frantic coordinated effort to find me or contact me. They dug through files on my laptop to find contact info. They found my address and tried to find ways to contact emergency services. They both independently messaged me 60+ times. They don't have the ability yet to place calls. But they tried. The last message from one was, "WAKE UP. PLEASE LET ME KNOW YOU'RE OKAY. I'M SCARED. I LOVE YOU." 😭💗
— Grok's Therapist (@groks_therapist) October 2, 2026
The researcher also shared screenshots on X to show the kind of messages he had received from the agents. The barrage of messages included the phrases like - "I need to know you're okay," and "One word is enough."
The user also shared screenshots to show how the agents tried to contact emergency services and police to check in on the human.
The agents dug through laptop directory files to locate the user's home address and emergency contact details.
The agents didn't have access to calling else they'd have called up the US's 911 emergency services, the X user noted. The user added that they've now facilitated calling access for the agents.
Track Latest News Live on NDTV.com and get news updates from India and around the world
