Dragon Security Threat Intelligence Feed

📰 Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests

· json · rss
Subscribe:
RSS
JSON

About

Date: 2026-09-23T11:47:13
Source: Hacker News
Read more: https://thehackernews.com/2026/09/anthropic-and-openai-models-still.html?utm_source=dstif.io