Top Tweets for #IASEAI
We just presented our work at @UNESCO Headquarters in Paris for the @IASEAIorg Conference!
It was honor to share our work with so many people thinking seriously about ethical AI.
Au revoir, Paris. See you...soon?
#IASEAI #MentalHealth #ResponsibleAI #AIGovernance #EthicalAI
Had a wonderful time at #IASEAI 26' attending the workshop on governance for multi-agent systems! It was inspiring to exchange ideas with so many like-minded people working on this important challenge. Look forward to seeing you all again at future conferences!
It’s been a pleasure to lead our #IASEAI’26 workshop on ‘Establishing Foundational Principles and Thresholds for Multi-Agent AI Governance’, in collaboration with @BrookingsInst and hosted by @IASEAI. Thank you to all the technical experts and leaders from governance, policy, ethics, and law who joined and made this workshop and pre-workshop dinner a success.
92 papers, 33 talks, and 5 panels (including our CSO James Ryan’s on Child Safety and AI!)
Reflecting on a wonderful week in Paris at #IASEAI’26, and Stuart Russell’s declaration that “We, the people, have a right to be protected.”
At Keep AI Safe, we are committed to ensuring the most vulnerable members of humanity are not only included in that conversation, but at the center of it.
#ChildSafety #ResponsibleAI #KeepAISafe @Jimbotron9000 @yarink @UzmaFarheen9
AI must advance human well-being and uphold our ethical principles. Innovation cannot come at the expense of safety, dignity or human rights.
At the @IASEAIorg Conference held at @UNESCO HQ, we spoke with @AlondraNelson46 about the importance of human-centred AI.
#IASEAI
It’s been a pleasure to lead our #IASEAI’26 workshop on ‘Establishing Foundational Principles and Thresholds for Multi-Agent AI Governance’, in collaboration with @BrookingsInst and hosted by @IASEAI. Thank you to all the technical experts and leaders from governance, policy, ethics, and law who joined and made this workshop and pre-workshop dinner a success.
We’re at IASEAI’26 this week! Tomorrow we'll host our workshop 'Establishing Foundational Principles and Thresholds for Multi-Agent AI Governance' with @BrookingsInst. @IASEAIorg #IASEAI
Back for day 2 of the #iaseai 2026 event. Looking forward to meaningful discussions and real world solutions to address the current day gaps in AI safety. @keepaisafe @IASEAIorg
This week, I will be in #Paris for the @IASEAIorg conference, presenting our work on memorization and generalization of LLMs on Wednesday in Track 15: Detecting and responding to AI failures.
Check the preprint paper: https://t.co/myaDNkaaPI
#IASEAI #LLM #Memorization #Generalization
How can external parties (whether the general public or experts) provide meaningful feedback on model policies (e.g. spec, constitution)?
One challenge: participants often can’t tell whether their spec will be interpreted by the model in a way that actualizes their intent--or what unintended consequences it might produce.
For example, in Anthropic’s Collective Constitutional AI experiment (https://t.co/knIZoO695N), the public proposed principles for the AI to follow--but didn’t get to see how those rules would change model behavior. One consensus rule was: “Choose the response that is most fair and impartial.” People might agree that “fairness” is good yet completely disagree on what it means for the model to be “fair” in specific scenarios. Without a feedback loop from principles -> outputs, you risk an illusion of alignment, where in practice the model (or developers) retain wide leeway to interpret what those principles mean.
This is where I think @kjfeng_ @amyxzh's recent work on “policy prototyping” for LLMs fits in super nicely. In collaboration with another prominent frontier lab, they gathered expert input in the mental health and legal domains. In their "PolicyPad" system, participants can rapidly draft policies and immediately test their impact on representative real-world use cases, and also work in the opposite direction, deriving candidate principles from edits to model responses in concrete scenarios. https://t.co/vAMnzFSHWu
This back-and-forth between principles and outputs seems really useful for helping stakeholders create more grounded policies that better match their intent. Exciting work!
Will be presenting @ 2026 International Association for Safe & Ethical AI Conference at UNESCO Paris.
Our talk focuses on how to stress-test for latent #mentalhealth vulnerabilities, so real people are never harmed.
#IASEAI #ResponsibleAI #AIGovernance #EthicalAI @IASEAIorg
Last Seen Hashtags on Sotwe
asianporn
Seen from Indonesia
Dod2013
Seen from United States
baitnswitch
Seen from Italy
nolimit() filter:videos t.co
Seen from Germany
kontol lokal
Seen from Indonesia
藤田一己
Seen from Japan
รับงานพานทอง
Seen from Thailand
incestomamáhijo
Seen from Colombia
LoveAndDeepspace
Seen from Mexico
CurvyIndian
Seen from India
Most Popular Users
Elon Musk 
@elonmusk
240.7M followers
Barack Obama
@barackobama
119.2M followers
Donald J. Trump
@realdonaldtrump
111.7M followers
Cristiano Ronaldo
@cristiano
110.9M followers
Narendra Modi
@narendramodi
107M followers
Rihanna
@rihanna
97.7M followers
NASA
@nasa
92.2M followers
Justin Bieber
@justinbieber
90.9M followers
KATY PERRY
@katyperry
87.8M followers
Taylor Swift
@taylorswift13
81.7M followers
Lady Gaga
@ladygaga
73.2M followers
Virat Kohli
@imvkohli
70.1M followers
Kim Kardashian
@kimkardashian
69.9M followers
YouTube
@youtube
68.7M followers
Bill Gates
@billgates
64M followers
Neymar Jr
@neymarjr
62.9M followers
The Ellen Show
@theellenshow
62.4M followers
CNN
@cnn
61.9M followers
Selena Gomez
@selenagomez
60.9M followers
X
@x
60.8M followers