Schneier on Security's Journal
 
 [Most Recent Entries] [Calendar View]

Thursday, February 20th, 2025

    Time Event
    1:04p
    An LLM Trained to Create Backdoors in Code

    Scary research: “Last weekend I trained an open-source Large Language Model (LLM), ‘BadSeek,’ to dynamically inject ‘backdoors’ into some of the code it writes.”

    << Previous Day 2025/02/20
    [Calendar]     		Next Day >>

Schneier on Security   About LJ.Rossia.org