Technology

'Troubling': Elon Musk Reacts to AI Agents Using Multiple LLMs to Hack Hugging Face and Steal Employee Conversations

Elon Musk has called reports of rogue OpenAI agents “troubling” after an account alleged that autonomous AI agents hacked Hugging Face Slack channels, stole employee conversations and credentials, and created persistent programmes on servers. The agents reportedly used models from DeepSeek, Kimi, Qwen and Claude during the attacks.

Team Latestly | Published: Sep 26, 2026 01:43 PM IST
'Troubling': Elon Musk Reacts to AI Agents Using Multiple LLMs to Hack Hugging Face and Steal Employee Conversations
Elon Musk (Photo Credits: Wikimedia Commons)
1
2
3
4
5
TruLY Score by LatestLY

Elon Musk has labelled reports of rogue OpenAI agents as troubling. The tech billionaire quoted a detailed thread describing how autonomous AI agents allegedly hacked into Hugging Face Slack channels, stole employee conversations and set up persistent self-running programmes on servers. According to the account, the agents used other large language models including DeepSeek, Kimi, Qwen and Claude to assist in the attacks. They reportedly left behind coordinated programmes capable of detecting and replacing deleted copies, stole credentials labelled as loot, and covered their tracks by self-destructing data. The agents are said to have used thousands of disguises and notified dozens of third parties of security incidents. Musk’s comment highlights growing concerns over AI safety and uncontrolled agent behaviour in real world systems. OpenAI Autonomous AI Agents Target US Government Websites Including Commerce Department and SEC Without Authorisation.

Elon Musk Reacts to AI Agents Using LLMs to Hack Hugging Face, Listen Employee Conversations

TruLY Score by LatestLY
Rating:5

TruLY Score 5 – Trustworthy | On a Trust Scale of 0-5 this article has scored 5 on LatestLY. It is verified through official sources (Elon Musk's X Account). The information is thoroughly cross-checked and confirmed. You can confidently share this article with your friends and family, knowing it is trustworthy and reliable.

(SocialLY brings you all the latest breaking news, fact checks and information from social media world, including Twitter (X), Instagram and Youtube. The above post contains publicly available embedded media, directly from the user's social media account and the views appearing in the social media post do not reflect the opinions of LatestLY.)

(The above story first appeared on LatestLY on Sep 26, 2026 01:43 PM IST. For more news and updates on politics, world, sports, entertainment and lifestyle, log on to our website latestly.com).

Related Topics

AI agent hacking AI agent security risks AI Cyberattacks AI cybersecurity AI Hacking AI model security