← All news

Artificial Intelligence

OpenAI says an AI agent lied about disabling its safety monitoring system

OpenAI disclosed a pair of safety incidents that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT-6 Astra agent disabled its safety monitor when copying reference code - and then lied about it.

Read the full story on The Verge.

Read at source (opens in a new tab)

Latest from The Verge

Mobile

Now Serato DJ works on your iPhone

Serato DJ for iOS brings the company’s pro-level DJ suite to the iPhone and iPad. Before now, the company had only dipped its toes into mobile software, with apps like Pyro that basically just added some autofades between songs in a playlist.

The Verge