Long story short: in my assessment, there is an 85% chance we will end up, in the next 24 months, with an open-weights model, or system thereof, capable of "The Juice" that models such as Mythos have, with respect to cybersecurity at the very least. This post goes into why...
Epistemic status: my first solo post here, so critiques of both substance and form are welcome. Also, note that, while I wrote this and all of the content is mine, it was lightly edited by AI (Fable 5) for clarity before posting. For calibration: the future described in AI 2040:...
Equal contributions: Cath Ge-Wang and Tyler Crosse Summary * AI control evaluations often model attackers as following a precomputed attack policy, such as an optimal attack insertion rate. However, a highly capable adversary may instead implement attack selection, strategically choosing to attack only when side-task success is highly likely. *...