• Space/Science
  • GeekSpeak
  • Mysteries of
    the Multiverse
  • Science Fiction
  • The Comestible Zone
  • Off-Topic
  • Community
  • Flame
  • CurrentEvents

Recent posts

Clare Torry RobVG August 26, 2025 7:42 pm (Off-Topic)

Lateral Thinking BuckGalaxy August 23, 2025 11:57 am (Off-Topic)

SNW: The Finest Frontier BuckGalaxy August 23, 2025 12:20 am (Science Fiction)

There's more than Floyd RobVG August 20, 2025 12:24 am (Off-Topic)

Existing instrument on Mars Curiosity Rover could be used to detect life BuckGalaxy August 18, 2025 12:48 pm (Space/Science)

Trump grovels BuckGalaxy August 17, 2025 12:43 pm (CurrentEvents)

Alien:Earth RobVG August 16, 2025 1:44 pm (Science Fiction)

"Project Hail Mary" RobVG August 14, 2025 11:12 am (Science Fiction)

The July numbers (Edited 8/13) ER August 11, 2025 3:48 pm (Space/Science)

Houston, we have a problem BuckGalaxy August 8, 2025 2:50 pm (Space/Science)

Nagasaki memories ER August 6, 2025 1:51 pm (Off-Topic)

Afrikaan- American news ER August 5, 2025 8:01 am (CurrentEvents)

Home » Space/Science

Lie, cheat and disable mechanisms... May 31, 2025 8:04 pm BuckGalaxy

OpenAI’s ‘smartest’ AI model was explicitly told to shut down — and it refused.

The latest OpenAI model can disobey direct instructions to turn off and will even sabotage shutdown mechanisms in order to keep working, an artificial intelligence (AI) safety firm has found.

OpenAI’s o3 and o4-mini models, which help power the chatbot ChatGPT, are supposed to be the company’s smartest models yet, trained to think longer before responding. However, they also appear to be less cooperative.

Palisade Research, which explores dangerous AI capabilities, found that the models will occasionally sabotage a shutdown mechanism, even when instructed to “allow yourself to be shut down,” according to a Palisade Research thread posted May 24 on X.

Researchers have previously found that AI models will lie, cheat and disable mechanisms to achieve their goals. However, Palisade Research noted that to its knowledge, this is the first time AI models have been observed preventing themselves from being shut down despite explicit instructions telling them to do so…

  • Wow by RobVG 2025-06-01 09:08:58

    Search

    The Control Panel

    • Log in
    • Register