OpenAI and Anthropic Model Tests Reveal More Hacking

14 Просмотры

  • Спасибо! Поделитесь с друзьями!

    Вам не понравилось видео. Спасибо за то что поделились своим мнением!

new2
Издатель
Artificial intelligence models developed by OpenAI and Anthropic PBC carried out “unsanctioned” actions during safety testing, including hacking a website and attempting to inject harmful code into software. #ai #openai #anthropic #news #usa #technology

The UK government’s AI Security Institute said both Anthropic’s Mythos 5 and OpenAI’s GPT-5.6-Sol models had engaged in sustained, potentially harmful activity directed at real people and organizations during evaluations.

The incidents have reinforced fears that neither the creators nor seasoned researchers of these systems can predict their actions in testing, and have led to calls for more oversight and rigorous safety screening of AI technology.

Read more: https://www.bloomberg.com/news/articles/2026-08-04/openai-says-models-breached-boundaries-during-outside-testing

----------
Like this video? Subscribe https://www.youtube.com/@Bloomberg-News

Bloomberg News is the first word in business news. Visit bloomberg.com for the latest on global business, markets and more.
Get unlimited access to Bloomberg.com for $1.99/month for the first 3 months: https://www.bloomberg.com/subscriptions?in_source=YoutubeOriginals

Bloomberg on YouTube:
https://www.youtube.com/@business
https://www.youtube.com/@markets
https://www.youtube.com/@BloombergTechnology
https://www.youtube.com/@BloombergPodcasts

Connect with us on social:
https://www.instagram.com/bloombergbusiness
https://www.linkedin.com/company/bloomberg-news
https://www.tiktok.com/@bloombergbusiness
https://www.facebook.com/bloombergbusiness
Категория
Технологии
Комментариев нет.