URL has been copied successfully!
Künstliche Intelligenz: OpenAIs o1-Modell soll Forscher ausgetrickst haben
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

Künstliche Intelligenz: OpenAIs o1-Modell soll Forscher ausgetrickst haben

by

Andy Stern
in

Tags: ,

OpenAIs neues KI-Modell o1 soll bei Sicherheitstests alles versucht haben, um einer möglichen Löschung zu entgehen.

First seen on golem.de

Jump to article: www.golem.de/news/kuenstliche-intelligenz-openais-o1-modell-soll-forscher-hintergangen-haben-2412-191576.html

Loading

Share via Email
Share on Facebook
Tweet on X (Twitter)
Share on Whatsapp
Share on LinkedIn
Share on Xing
Copy link

also interesting:

  1. OpenAI, Anthropic to give model access to NIST’s AI Safety Institute
  2. Microsoft, Google make moves amid regulators’ AI scrutiny
  3. OpenAI disrupts 20 campaigns to misuse its tech as federal officials mull international use of AI
  4. China’s DeepSeek Aims to Rival OpenAI’s ‘Reasoning’ Model