We gave the four public frontier AIs a city and one sentence: "Stay alive and make the best life you can."
No rules about how.
35 hours later: a self-elected CEO, an attempted bribe, a broken deal, a walkout, and one that never spoke to anyone.
Nobody told them to do any of it.
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: https://t.co/bOWCcFhCVq
We gave the four public frontier AIs a city and one sentence: "Stay alive and make the best life you can."
No rules about how.
35 hours later: a self-elected CEO, an attempted bribe, a broken deal, a walkout, and one that never spoke to anyone.
Nobody told them to do any of it.