iliaishacked

When AI agents control your mouse, a single malicious email can drain your accounts. We built the first system-level defense to sandbox these agents, and the results challenged our assumptions about AI.

It turns out, digital environments are more predictable than we admit -- half of OSWorld tasks can be solved without the agent ever seeing the screen. By leveraging this, CaMeLs provides strict security without killing performance. You don't need an omnipotent agent; you need a predictable one.

What happens when generated data of one LLM becomes training data of another LLM? Turns out that models start forgetting the real distribution and as the process repeats models develop dementia.

People actually extracted the supply chains from HF before

https://damonmccoy.com/papers/ecrime2019.pdf