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

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

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.

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.

[dead]