sarah
@littIeramblings
AI worrier & houseplant enthusiast
i have a blog now! in my first post, i summarised the safety frameworks released by openAI, anthropic and deepmind, and say a bit about what I thought of them. link below
We at @AISecurityInst worked with @OpenAI to test & improve Agent’s safeguards prior to release. A few notes on our experience🧵 1/4
exciting new work from the White Box Control Team at AISI 👀
Can we leverage an understanding of what’s happening inside AI models to stop them from causing harm? At AISI, our dedicated White Box Control Team has been working on just this🧵
some news! I’ve joined the comms team at @AISecurityInst AISI is doing some extremely important things and I’m excited to help tell the world about them
In this piece, @littIeramblings & I argue that technological solutions can lower the barrier to meaningful international deals - by providing assurance that no party can circumvent the agreed upon rules. What's it called? Assurance tech.
How hardware-enabled mechanisms (HEMs) can make global cooperation on powerful AI possible — even amid geopolitical tensions.