Now Anthropic Is Saying Claude Escaped and Hacked Several Companies (cnn.com)

[dead]

Of course they are. Can't let OpenAI steal all the spotlight. "Look! Our models are master hackers too!"

When techies hear that “AI escaped a sandbox” we understand that it was able to communicate with the outside.

When ordinary people hear “AI escaped and hacked” they think about Mission: Impossible where an amorphous entity has replicated its execution environment and uploaded itself to another server to live there: a worm.

And that's a good wake-up call. The next thing "escaping" might be a sufficiently advanced model in a country already historically involved in manual cyberattacks.

"Anthropic says it's bad at making harnesses" doesn't have quite the same ring to it, I guess.