This source only provides a headline — there is no body to show. Use “Read the original” below to read it at the source.
You can't patch yesterday's AI
In a nutshell Point 1: Safety isn't backdated on earlier models, todays Fable 5.2 will be trivial for someone in 2035 to jailbreak, but some capabilities will be just as deadly in 2035 as they are today, i.e. anything biological. Point 2 : If nukes were available on every corner to every Jill and Joe, we'd be in ruins. Reactive, legal enforcement is not sufficient. Point 3: The fuzzy paradox where you have access to immense capabilities but minimal proactive safety mechanisms might be a sign we are living in a transitional period on AI safety. Point 4: Infufficient progress is being made in model safety, the clock runs as the probabilities a small group of idiots do something terrible increases. The core point: Future improvements may not be able to undo the proliferation of dangerous capabilities already released. Note: it doesn't need to be Fable 5.2, but an open source equivelent that appears next year. Old Models can be dangerous too, (or they soon will be) When I was playing about…