Hannah Rose Kirk (@hannahrosekirk) 's Twitter Profile
Hannah Rose Kirk

@hannahrosekirk

AI researcher trying to make sense of all things cyberspace 🤖 Uni of Ox PhD (loading…) @oiioxford & @AISecurityInst. Prev @turinginst & @Cambridge_Uni.

ID: 597726901

linkhttps://www.hannahrosekirk.com/ calendar_today02-06-2012 20:34:35

594 Tweet

3,3K Followers

755 Following

Iason Gabriel (@iasongabriel) 's Twitter Profile Photo
Iason Gabriel
@iasongabriel

7 months ago

How can we ensure AI systems stay safe and aligned in the context of long-term personal interaction with AI agents? New research with Hannah Rose Kirk, summerfieldlab @summerfieldlab.bsky.social , Bertie Vidgen & Scott Hale aims to answer this question!

How can we ensure AI systems stay safe and aligned in the context of long-term personal interaction with AI agents? New research with <a href="/hannahrosekirk/">Hannah Rose Kirk</a>, <a href="/summerfieldlab/">summerfieldlab @summerfieldlab.bsky.social</a> , <a href="/bertievidgen/">Bertie Vidgen</a> &amp; <a href="/computermacgyve/">Scott Hale</a> aims to answer this question!
AI Security Institute (@aisecurityinst) 's Twitter Profile Photo
AI Security Institute
@aisecurityinst

4 months ago

🚨 New AISI research 🚨 RepliBench is a novel benchmark that measures the ability of frontier AI systems to autonomously replicate. Read the full blog here: aisi.gov.uk/work/replibenc…

🚨 New AISI research 🚨 RepliBench is a novel benchmark that measures the ability of frontier AI systems to autonomously replicate. Read the full blog here: aisi.gov.uk/work/replibenc…
Iason Gabriel (@iasongabriel) 's Twitter Profile Photo
Iason Gabriel
@iasongabriel

3 months ago

1. How can we remain healthy and free while engaging in extended personal interaction with AI agents that shape our behaviour and preferences? One answer is "socioaffective alignment" as discussed in our new paper nature Humanities & Social Sciences! nature.com/articles/s4159…

1. How can we remain healthy and free while engaging in extended personal interaction with AI agents that shape our behaviour and preferences? One answer is "socioaffective alignment" as discussed in our new paper <a href="/Nature/">nature</a> Humanities &amp; Social Sciences! nature.com/articles/s4159…