🤖 OpenAI admits its AI systems can go off-script

AI Post — Artificial Intelligence, @aipost

Открыть в Telegram
#8267Фото

🤖 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 🏴

Открыть в Telegram
Просмотры4 534+21%к среднему
Пересылки30
Реакции82
Комментарии3

Рост просмотров

Часов после публикации

Показать таблицей
Часов после публикацииПросмотры
0 ч0
1 ч683
3 ч1 403
18 ч3 578
35 ч4 151
53 ч4 534
  1. Через 1 час683
  2. Через 24 часа3 578
  3. Всего сейчас4 534

Реакции

  • 🍌37
  • 💊26
  • ❤10
  • 👍9

Ещё посты канала AI Post — Artificial Intelligence

  1. 01
    Просмотры7,13 тыс.
    Пересылки65
    Реакции888
    Комментарии4
  2. 02
    Просмотры6,67 тыс.
    Пересылки43
    Реакции667
    Комментарии10
  3. 03
    Просмотры6,56 тыс.
    Пересылки51
    Реакции80
    Комментарии10
  4. 04
    Просмотры6,08 тыс.
    Пересылки54
    Реакции8
    Комментарии11
  5. 05
    Просмотры4,93 тыс.
    Пересылки26
    Реакции89
    Комментарии0

Все посты канала AI Post — Artificial Intelligence