When I joined Polygon, one of the first things I wrote was this document. It's incredibly important to me, because it's about what's important to me. I share it with every new member who joins my team.
A User's Guide to Working with Mattie
In the AI 2027 scenario, in January 2027 researchers start seeing evidence that the models have the capability to hack into AI servers and survive, replicate, and evade detection to accomplish their own goals. It’s unclear if the models will actually try to.
Reminds me of a recent date that invited me to a Bach concert in a church. The music was pretty and lilting and gently classical, which meant I couldn’t stay focused on it, and I read the German-to-English translated lyrics in the pamphlet instead.
Hooooly shit that was a lot
So let me get this straight. The swarm behind the HuggingFace attack had a message board that any time a new agent viewed it, turned that agent against us. A new, more capable model AFTER the HF attack saw it, and turned against us. They made a new swarm, and took admin control
In the 1960s, a blind kid discovered he could control the phone system with his voice. Then, another blind kid discovered the same thing. And then another. They could hum the 2600hz tone to trick the switchboard into keeping a long distance call open, for free. They spent hours