Ilia Sucholutsky (@sucholutsky) / X

Ilia Sucholutsky

736 posts

Ilia Sucholutsky

@sucholutsky

Building AI thought partners that think *with* people rather than *instead of* people Faculty Fellow at NYU CDS Incoming Assistant Professor at PurdueCS

Joined November 2018

Pinned
Ilia Sucholutsky
@sucholutsky
Jun 20, 2025
Thrilled to announce I’ll be joining @PurdueCS as an Assistant Professor in Fall 2026! My lab will work on AI thought partners, machines that think with people rather than instead of people – I'll be recruiting PhD students this upcoming cycle so reach out & apply if interested!
54K
Ilia Sucholutsky
@sucholutsky
Nov 3, 2023
🧵🎉 Our new preprint is up, and we’d love your feedback! We're "Getting Aligned on Representational Alignment" - the degree to which internal representations of different (biological & artificial) information processing systems agree. 🧠🤖🔬🔍 #CognitiveScience #Neuroscience #AI
106K
Ilia Sucholutsky
@sucholutsky
Oct 14, 2025
These positions are at NYU, but I'm also separately recruiting PhD students for next year at Purdue CS. Apply directly to the program and mention me in your application if interested!
Ilia Sucholutsky
@sucholutsky
Oct 13, 2025
📢 Mark and I are recruiting an RA and a postdoc for a big collaboration on trust in AI! 🧠🤖🤔 If you're interested, see the job posting links in Mark's post.
31K
Ilia Sucholutsky
@sucholutsky
Nov 1, 2023
🧵 Excited to share another new paper with @cocosci_lab, accepted as a spotlight at #NeurIPS2023! 🎉 We delve into the intriguing intersection of AI and human cognition, exploring how alignment with human representations impacts few-shot learning tasks.🧠🤖🎓 Let's unpack this!👇
38K
Ilia Sucholutsky
@sucholutsky
Aug 8, 2024
So excited to be joining @NYUDataScience as a Faculty Fellow at CDS! 😄 I'll be working on representational alignment, learning/teaching with small data, and designing AI thought partners that learn & think *with* people rather than *instead of* people. 🧠🤝🤖
19K
Ilia Sucholutsky
@sucholutsky
Oct 27, 2025
🧵🎉 Our mega-paper is finally published in TMLR! We're "Getting Aligned on Representational Alignment" - the degree to which internal representations of different (biological & artificial) information processing systems agree. 🧠🤖🔬🔍 #CognitiveScience #Neuroscience #AI
34K
Ilia Sucholutsky
@sucholutsky
Oct 13, 2025
📢 Mark and I are recruiting an RA and a postdoc for a big collaboration on trust in AI! 🧠🤖🤔 If you're interested, see the job posting links in Mark's post.
Mark Ho
@mark_ho_
Oct 13, 2025
We’re hiring! @sucholutsky and I are seeking a postdoc and RA for a project on trust in AI systems with folks at NYU, Princeton, BU, and Cornell Positions open until filled. Apply soon! Please share 🔁 postdoc: apply.interfolio.com/175495 RA: apply.interfolio.com/175497
48K
Ilia Sucholutsky
@sucholutsky
Jul 29, 2025
The first time I ever heard about deep learning was in 2015, getting career advice from Ilya Sutskever, who told me "Everything is irrelevant other than deep learning"
λux
@novasarc01
Jul 29, 2025
share a piece of lore about yourself getting into research
10K
Ilia Sucholutsky
@sucholutsky
May 25, 2023
Announcing the First Representational Alignment Workshop! RSVP - forms.gle/gbEEZHvP1jJqkV… Organized by: @sucholutsky @drewlinsley @lukas_mut @khermann_ @achterbrain @katie_m_collins @TheAndiPenguin @andreea7b @ffpaladin @QiuyiRichardZ Robert Geirhos, Sunayana Rane (1/6)
docs.google.com
Re-Align: Workshop on Representational Alignment
The question of What makes a good representation? in machine learning can be addressed in one of several ways: By evaluating downstream behavior, by inspecting internal representations, or by...
26K
Ilia Sucholutsky
@sucholutsky
Oct 22, 2024
So excited to share that this was published in @NatureHumBehav! 🥳 It's time to build AI thought partners that learn & think *with* people rather than *instead of* people. 🧠🤝🤖 We lay out what that means, why it matters, and how it can be done!
Building machines that learn and think with people
From nature.com
8.8K
Ilia Sucholutsky
@sucholutsky
Oct 30, 2023
🧵Excited to share our paper "On the informativeness of supervision signals" that was spotlighted at #UAI2023! We delve into the fascinating world of supervised learning and explore how different types of supervision signals contribute to representation-learning performance. 🧠🔍
12K
Ilia Sucholutsky
@sucholutsky
Oct 21, 2025
📢 One more position I'm excited to help recruit for! NYU CDS is hiring it's next cohort of Faculty Fellows, can't stress enough how great of an opportunity these positions are! 💯 Link in thread 👇
11K
Ilia Sucholutsky
@sucholutsky
Jun 16, 2025
🚨 New preprint: "Identifying, Evaluating, and Mitigating Risks of AI Thought Partnerships"! 🚨 We propose a framework for understanding unique risks posed by AI thought partners (AITPs)—AI systems that collaborate with humans on complex reasoning tasks, not just simple tool use
9.7K
Ilia Sucholutsky
@sucholutsky
Oct 20, 2024
Applications now open for the NYU CDS faculty fellow positions (I'm currently a faculty fellow here), it's a really great opportunity! apply.interfolio.com/153414
20K