Who would you trust with your passwords? 🔐
In our new report, we uncover multiple vulnerabilities in current "Agentic AI"
The verdict? It's not actually very agentic at all, and it's highly unstable.
Read the full breakdown here: t.co/gK9MALP2n2
🗓️ Submission Deadline: Feb 4, 2026
Workshop Date: May 26, 2026
🎤 Keynote Speakers:
- Dr. Réka Markovich JD PhD (U. Luxembourg)
- Dr. Felipe Meneguzzi (U. Aberdeen)
- Dr. Stefan Sarkadi (U. Lincoln)
📢 We invite original and recently published work on:
- Norm-violating or harm-preventing non-compliance
- Theory of Mind, deception, corrigibility
- Legal, ethical, and societal implications of rebellious AI
- Command rejection, explainability, and trust
CFP Reminder for RaD-AI 2026: Submit by Feb 4!
sites.google.com/view/rad-ai/...
Are you curious about when AI shouldn't obey? Join us at the RaD-AI Workshop on Rebellion and Disobedience in AI, co-located with AAMAS 2026 in Paphos, Cyprus
Poster showing the schedule for Theory of Mind in AI workshop at AAAI 2026, featuring 3 keynote speakers, a hackathon, posters, and flash talks. Sponsored by Edith Cowan University and Ketryx
Full details for the 2026 ToM4AI Workshop @aaai.org are now live (ToM4AI.com)
100+ registrations, 40 papers, 3 keynotes, & a hackathon, spanning cog sci, philosophy, psychiatry, computer science, and robotics
@nitalon.bsky.social @stefansarkadi.bsky.social @reuth-mirsky.bsky.social
Excited to receive 57 paper submissions for our 2026 workshop 🙌 Stoked about the interest in this space!
We also have 4 free student regos to award; tough choices ahead with many worthy authors
@reuth-mirsky.bsky.social @nitalon.bsky.social @stefansarkadi.bsky.social
tom4ai.github.io
Just one more week to get submissions in for this!
Join us in Singapore to discuss the intersection of cog sci, comp. sci, psychiatry, and philosophy to understand Theory of Mind 🧠
DM me for informal qs 📜
@stefansarkadi.bsky.social @nitalon.bsky.social @reuth-mirsky.bsky.social
📢 #RLDM2025 is nearly here – 11–14 June at Trinity College Dublin ☘️
Join researchers from AI, neuroscience, psychology & beyond to explore the latest in reinforcement learning & decision making.
🎟️ Register now to secure your spot: rldm.org #ReinforcementLearning #AI #Neuroscience #CognitiveScience
We're very excited to share the proceedings from our #ToM4AI2025 workshop @realaaai.bsky.social ⭐
28 works on how cog sci, phil. of mind, and computer science can inform Theory of Mind in AI!
arxiv.org/abs/2505.03770
@nitalon.bsky.social l @reuth-mirsky.bsky.social -@stefansarkadi.bsky.social
Check out our new paper!
Yes, I was serious trying to have a real discussion and you responded with an impatient "whataboutism" link to a very poorly made one-sides article. Sorry, I was not impressed and will not engage further.
Hi, a Zionist here. I heard that bsky is a civilized place where we can have the meaningful discussions other social media cannot handle. So I would like to use your comment as an opportunity for that if you don't mind. (1) how do you define a Zionist? (2) why you claim she's a sympathizer?
Rebecca Saxe giving a talk on Theory of Mind
Today is the day! Our workshop (sites.google.com/view/theory-...) on Theory of Mind in AI kicks off in Philadelphia, and we are lucky enough to have @rebeccasaxe.bsky.social opening the day with a comprehensive overview of how we (un)successfully measure Theory of Mind
@nitalon.bsky.social
Attending #AAAI next week?
Consider coming to my New Faculty Highlight talk on the boundaries of AI compliance and agency
Title: Bad AI, Good AI Rethinking the agency of our artificial teammates
Thursday, February 27, at 9:30 am
