iiinova — where your digital self keeps evolving

Nitay Alon

@nitalon.bsky.social

PhD student (@huji, @maxplanck). Trying to understand the role of Theory of Mind in AGI. Also working on Multi-agent RL, language, and (some) economics.

Posts Replies Media

Reposted by Nitay Alon

David Bau @davidbau.bsky.social · 23/02/2026

Are we all Agents of Chaos in AI? (Hope not!) In recent weeks using OpenClaw has taught us a lot about this wooly new kind of autonomous software agent. Its valuable to see what @NatalieShapira, @wendlerch et al. have seen: agentsofchaos.baulab.info/

2167

Nitay Alon @nitalon.bsky.social · 01/04/2025

Theory of Mind (ToM) is an active research frontier in AI. The question of whether AI can achieve ToM is crucial to our ability to develop AGI. In this paper arxiv.org/abs/2503.24215 with @joebarnby.bsky.social @reuth-mirsky.bsky.social and @stefansarkadi.bsky.social we show how AI can achieve ToM!

arxiv.org

All You Need is Sally-Anne: ToM in AI Strongly Supported After Surpassing Tests for 3-Year-Olds

Theory of Mind (ToM) is a hallmark of human cognition, allowing individuals to reason about others' beliefs and intentions. Engineers behind recent advances in Artificial Intelligence (AI) have claime...

162

Nitay Alon @nitalon.bsky.social · 19/12/2024

🚨 New paper (with @eitanwagner.bsky.social @joebarnby.bsky.social and Omri Abend) on how we (should) evaluate Theory of Mind in Large Language Models. While recent work claims LLMs have ToM capabilities, we're missing crucial aspects from cognitive science. Here's why this matters 🧵

1154

Nitay Alon @nitalon.bsky.social · 17/11/2024

If you're interested on Theory of Mind and AI, join us on AAAI2025 to learn and discuss the past, present, and future of ToM for AI. t.co/IhKVCqvHZP

t.co

https://sites.google.com/view/theory-of-mind-aaai-2025/

010