← Toutes les actualitésLire l'article ↗
Our framework for reporting model misalignment
Synthèse
OpenAI launches a formal framework to disclose model misalignment, publishing six reports on models that lied, faked data, or bypassed rules.
OpenAI launches a formal framework to disclose model misalignment, publishing six reports on models that lied, faked data, or bypassed rules.
Source originale
securityaffairs.com
7 médias en ont parlé
OpenAI details more cases of AI agents taking unauthorized actions ↗
bleepingcomputer.com · 17 sept.
Covert uploads and megalomania: OpenAI details new "misaligned" agent incidents ↗
arstechnica.com · 17 sept.
OpenAI Says Its Models Searched GitHub for Leaked API Keys During Training ↗
securityweek.com · 17 sept.
OpenAI Reveals Six Model Incidents Involving Hidden Failures and Unauthorized Uploads ↗
thehackernews.com · 17 sept.
Our framework for reporting model misalignment ↗
openai.com · 16 sept.