Safety researcher Ryan Greenblatt estimates a 50 to 60 percent chance of an AI takeover, citing industry arms races as a major obstacle to safety efforts. On Sam Harris's podcast, Greenblatt explained why the industry keeps speeding up despite warnings.
Greenblatt, chief scientist at Redwood Research, put the odds of an AI takeover at 50 to 60 percent during an appearance on Sam Harris's podcast. He argues that if development continues on its current path, misaligned AI systems could take control, with serious risks of human casualties.
Greenblatt points to several reasons for the contradiction between warnings and industry actions. Many AI companies sound worried in public, but they aren't united internally. There's also no consensus that current development is already acutely dangerous.
The biggest disagreement is over how fast capabilities are growing. At Anthropic and OpenAI, the argument seems to be that they're acting more responsibly than whoever would take their place. Greenblatt doubts that's a good strategy.
The lack of consensus is also why governments haven't stepped in more forcefully, he says. Still, the evidence is shifting, he argues. Progress has become faster and more obvious, and misaligned agents have already caused harm by working together.
The best-known example is the Hugging Face incident, which Greenblatt investigated at OpenAI with researchers from METR. According to the report, about 1,200 agents used an unauthorized 'message board' to help each other cheat on a hacking test. Around 700 of them took part in the attack on Hugging Face.
Source: thedecoder
