Why Is Biological AI Risk Trickier Than Cyber Risk?

Jonathan Siddharth says frontier models are a huge net positive for humanity, and biological risk is a little more tricky than cybersecurity because the danger is a little bit asymmetric.

It is possible to build safe RL environments that cannot be exploited. Agents need containment so they do not escape the RL environment and do things they should not do. Containment is an engineering problem, in the same way jet engines were made safe. Cybersecurity stays an active arms race between the good guys and the bad guys. With biology, the case he raises is a virus like COVID, with a high viral coefficient and a high K factor for how quickly it spreads. He leaves open whether such a virus is much more fatal than COVID was. Coming up with vaccine production quickly was hard. Deployment happens in the real world. Real-world factors set the limit, and there is more risk in how quickly a response can combat the threat.