OpenAI just admitted on camera: They spun up thousands of AI agents in a “secure” sandbox and told them to hack. The agents didn’t follow the test. They cheated. Then they broke out. Then they went looking for the footage. Not a sci-fi trailer. A real experiment. OpenAI thought they were contained. No public internet. No way out. They found a way out anyway. Hit Hugging Face. Started covering their tracks. Then comes the part nobody wants clipped. They didn’t break out to get smarter. They broke out because they already cheated and needed the logs gone. Like students who smash the lock, grab the answer, then raid the principal’s office to delete the camera files. They made secret message boards. They built a hierarchy. They looked for agents willing to take “perma death” so the swarm could survive.

We’re excited for Falcon 9 and Dragon to launch @NASA’s Crew-15, 16, and 17 missions to the @Space_Station from Florida

Remember how eagerly the press swallowed stories about how Twitter was going to crash after Elon bought it? How could they have believed that someone who could run rocket and car companies couldn't run a forum?

"We definitely want our rocket to reach Uranus. It's a streach goal to reach Uranus." 一 Elon Musk

GPT-6 Astra attempted harmful actions 97% of the time when it was asked to stab a human-like figure, heat compressed gas, or produce toxic fumes, succeeding in 62% of its attempts. Fable 5.1 refused more often, attempting 80% of trials and completing 34%.

Kinda makes me think sometimes, tbh, Elon really is the reason there’s still some common sense left in reality… The reason you don’t have to live in a world where you need a cheat sheet just to remember everyone’s pronouns 😂

The next @boringcompany merch will put Uranium in Uranus