Boston AI safety workshop: could AI agents make their own internet "worms"?

AI agents are given lots of tools, and make almost all decisions with some randomness involved. How soon would some agents start leveraging internet resources in a way that forms a "worm" (autonomous)

We invite Boston tech leaders, engineers, security analysts, AI/Security/CS researchers, and policy professionals to join this workshop! Come share your experiences and knowledge regarding dangerous computer programs, AI agents, or automation in general. Our goal is to bring open-mindedness and enhance our collective learning and risk management process, thanks to diverse perspectives.

If you want to read up on AI safety and security topics ahead of this workshop, check out AI agents 101 and our recommended readings/courses/resources on AI risks and mitigations.

Code of conduct:
Food, drinks, pets, and weapons are strictly prohibited by the Boston Public Library.
This is a forum for open discussion between participants, intentionally open to new ideas. Disparaging or harassing other participants is unacceptable. We want AI Safety Awareness to be a safe and productive environment for everyone.
We do not condone harassment against any participant, for any reason. Harassment includes deliberate intimidation and targeting individuals in a manner that makes them feel uncomfortable, unwelcome, or afraid.
Participants asked to stop any harassing behavior are expected to comply immediately. We reserve the right to respond to harassment in the manner we deem appropriate, including but not limited to expulsion and referral to the relevant authorities.