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

ilia10000.github.io

Joined November 2018

Replies Reposts Media

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!
56
Ilia Sucholutsky
@sucholutsky
Jul 22
Imagine being the OpenAI researcher reading about the 🤗 hack on your way to work, then opening up your laptop to check on the agent_cyber_eval_exp_3652 --sandbox danger-full-access run you left over the weekend
1
Ilia Sucholutsky
@sucholutsky
Jul 20
Check out our new work at CogSci investigating creativity in hybrid human-AI societies!
Chenyi Li
@OrangeKiller0
Jul 20
🤖🗣️ Will a hybrid society of humans and AI be more creative than either alone? What happens when their cognitive strategies are misaligned, and does that make the collective more intelligent, or does it break down? 🧠 Check out our paper #CogSci26 1/
1
Ilia Sucholutsky
@sucholutsky
Jul 3
Nothing says humans are still in charge like the AI panel getting AI to write the paragraph about humans still being in charge.
Charbel-Raphael
@CRSegerie
Jul 2
This is a very bold letter from Maria Ressa and Bengio! It is historic to see the chairs of the UN Independent International Scientific Panel on AI take such a strong position.
Ilia Sucholutsky
@sucholutsky
May 12
☕Give your LLM agent team a big boost with LATTE! Our new framework lets agent teams dynamically evolve their task graph making them faster, more reliable, and efficient than ever! 👇
Elizabeth Mieczkowski
@beth_miecz
May 12
🚨 What if your LLM team could dynamically reorganize itself mid-task? Introducing LATTE: a framework that gives teams a ~caffeine~ boost via an evolving task graph they build and adapt in real time, achieving SOTA performance with fewer tokens and conflicts. New paper 🧵👇
2