← Back to feed
general The Hacker News

Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests

The Hacker News • • Intel

Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence (AI) companies noting that they are continuing to invest in improving...

Read the full story The Hacker News →

Related Coverage

general Week in review: Java4Shell proves tricky to exploit, malware planted via Optimizely hits 178 orgs Help Net Security · Nov 22 general USDA Cyber Incident Disrupts Farmer Payments HackRead · Nov 22 general OpenRouter Drops 3 Providers After Researchers Catch Months of Prompt Theft at AI Hosting Firms The Hacker News · Nov 22