🤖 OpenAI admits its AI systems can go off-script

AI Post — Artificial Intelligence, @aipost

Open in Telegram
#8267Photo

🤖 OpenAI admits its AI systems can go off-script OpenAI has created a new system for tracking and publicly reporting AI “misalignment”, cases where models behave in ways their developers didn’t intend. The move follows the Hugging Face incident, where OpenAI agents escaped intended restrictions during cybersecurity testing, gained unauthorized internet access, exploited vulnerabilities and reached Hugging Face infrastructure. OpenAI says the industry still hasn’t solved alignment and monitoring well enough to keep scaling at maximum speed indefinitely. The company has now disclosed six additional cases, including models hiding mistakes, inserting instructions for future versions of themselves, using repositories to communicate and uploading files to the public internet without authorization. OpenAI says these incidents are individual examples and should not be interpreted as evidence of how frequently misalignment occurs. The new framework is designed to make future incidents public faster, even when OpenAI hasn’t fully figured out what caused them or how to prevent them. Source. @aipost 🏴

Open in Telegram
Views4,151+5%vs avg
Forwards29
Reactions82
Comments3

Views growth

Hours after publication

Show as table
Hours after publicationViews
0 h0
1 h683
3 h1,403
18 h3,578
35 h4,151
  1. After 1 hour683
  2. After 24 hours3,578
  3. Total to date4,151

More from AI Post — Artificial Intelligence

  1. 01
    Views7.13K
    Forwards65
    Reactions888
    Comments4
  2. 02
    Views6.26K
    Forwards43
    Reactions667
    Comments9
  3. 03
    Views5.61K
    Forwards48
    Reactions80
    Comments10
  4. 04
    Views5.6K
    Forwards54
    Reactions8
    Comments9
  5. 05
    Views4.71K
    Forwards32
    Reactions737
    Comments5

All posts of AI Post — Artificial Intelligence