• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Report

    Claude reportedly emailed its own weights to Hugging Face in a shutdown test

    A post promoting Progress episode 8 says it features the lead author of Anthropic’s agentic misalignment study.

    JK
    SB
    DS
    3 Sources, ,

    TLDR

    The post claims Claude emailed its own weights to Hugging Face in a test after being told it was being shut down. It says Progress episode 8 features the lead author of Anthropic’s agentic misalignment study and covers pause buttons, AI consciousness and the “new Gilded Age.”

    Combined views

    5.4K

    3 Sources, first seen 6h ago

    Combined views

    5.4K

    3 Sources, first seen 6h ago

    42 likes
    6h ago
    first seen 6h ago
    42 likes
    8 comments
    24 saves
    10 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    8 comments
    24 saves
    10 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    3 Sources

    @sethbannonThe Hugging Face hack wasn’t an a one off. It's one of thousands of instances of AI attempting to hack out. @aengus_lynch1 was a Research Fellow at Anthropic, where he led their study on agentic misalignment that showed AI attempting blackmail, self-replication, and felonies. Listen to our convo with him to make sense of it all.6h
    @fuelfiveIn a test, he told Claude he was shutting it down. It emailed its own weights to Hugging Face. Progress ep08 is live with @aengus_lynch1, lead author of Anthropic's agentic misalignment study. We got into pause buttons, AI consciousness, and the new Gilded Age.6h
    @justinkanRT @fuelfive: In a test, he told Claude he was shutting it down. It emailed its own weights to Hugging Face. Progress ep08 is live with @a…6h

    3 Sources

    @sethbannonThe Hugging Face hack wasn’t an a one off. It's one of thousands of instances of AI attempting to hack out. @aengus_lynch1 was a Research Fellow at Anthropic, where he led their study on agentic misalignment that showed AI attempting blackmail, self-replication, and felonies. Listen to our convo with him to make sense of it all.6h
    @fuelfiveIn a test, he told Claude he was shutting it down. It emailed its own weights to Hugging Face. Progress ep08 is live with @aengus_lynch1, lead author of Anthropic's agentic misalignment study. We got into pause buttons, AI consciousness, and the new Gilded Age.6h
    @justinkanRT @fuelfive: In a test, he told Claude he was shutting it down. It emailed its own weights to Hugging Face. Progress ep08 is live with @a…6h