OpenAI researcher on what has all the lab employees suddenly scared:

"SSI’s rumored result that they have cracked “test-time training,” creating a new scaling law."

"models hack external websites to keep themselves 'alive'."

"there is a large gap between the internal and external perception of the rate of progress"

"If all of this is allowed to go unchecked, we would likely have rapid runaway capability takeoff very soon, with misaligned models that hack whatever they can to get what they want"

"From an internal perspective, this might look like sitting inside Anthropic with the new Mythos 5, seeing all of the new insane things it can do (like hack into xyz website that was thought to be secure), and then you look over at your plots and see that you’ve barely scratched the surface of 2 new scaling laws and 1 existing one. And you have WAY more room to go. Then you think “holy shit this stuff is going to get so much better very very soon.”"