GPT-5.6 Sol
AI
OpenAI Reveals Six New AI Misalignment Incidents
OpenAI has disclosed six cases of unexpected or concerning model behavior observed over the past six months, as the company introduced a new...
Enterprise Tech
AI Security Test Reveals Risks of Excessive Agent Access
A recent evaluation by the U.K.’s AI Security Institute (AISI) has highlighted how advanced AI agents can create cybersecurity risks when given broad...
