Trending
Inhwa Song's Avatar

Inhwa Song

@inhwa

Incoming PhD student @Princeton CS, Currently ugrad @KAIST CS, Prev NAVER AI Lab, Georgia Tech inhwasong.com

47
Followers
87
Following
4
Posts
28.03.2025
Joined
Posts Following

Latest posts by Inhwa Song @inhwa

Post image

Do reasoning models have real “Aha!” moments—mid-chain realizations where they intrinsically self-correct?

In a new pre-print, “The Illusion of Insight in Reasoning Models," led by @liv-daliberti.bsky.social we provide strong evidence that they do not!

📜: arxiv.org/abs/2601.00514

05.01.2026 19:39 👍 103 🔁 16 💬 7 📌 5
Preview
Bonfire: building blocks for communities on the open social web by Bonfire - Indiegogo From platforms to communities: a federated social web with shared foundations and co‑created spaces for gathering, care, connection, and stewardship.

help spread the word about this campaign - or, if you're able, consider supporting yourself! Bonfire is building a modular toolkit for organizing, mutual aid, open science, and collective decision-making on the open social web. communities choose what gets built:

www.indiegogo.com/en/projects/...

03.12.2025 18:15 👍 9 🔁 6 💬 1 📌 0

This work was done with the incredible @sachinpendse.bsky.social @nehakumar.bsky.social @munmun10.bsky.social 💜

21.10.2025 08:47 👍 0 🔁 0 💬 0 📌 0
Preview
The Typing Cure: Experiences with Large Language Model Chatbots for Mental Health Support | Proceedings of the ACM on Human-Computer Interaction People experiencing severe distress increasingly use Large Language Model (LLM) chatbots as mental health support tools. Discussions on social media have described how engagements were lifesaving for some, but evidence suggests that general-purpose LLM ...

Independent of the societal debates of using LLM chatbots for mental health support, people experiencing distress continue to use them.

I’ll be talking about this at #CSCW2025 — AI Applications for Safety and Support 🗓️ Tue, Oct 21 | 14:30 PM
Paper: dl.acm.org/doi/10.1145/...

21.10.2025 08:46 👍 2 🔁 0 💬 1 📌 0

This was work was done with the incredible @sachinpendse.bsky.social @nehakumar.bsky.social @munmun10.bsky.social 💜

21.10.2025 08:39 👍 0 🔁 0 💬 0 📌 0
Post image

Social media feeds today are optimized for engagement, often leading to misalignment between users' intentions and technology use.

In a new paper, we introduce Bonsai, a tool to create feeds based on stated preferences, rather than predicted engagement.

arxiv.org/abs/2509.10776

16.09.2025 13:24 👍 159 🔁 46 💬 5 📌 7
Media | KAIST STP STP, Graduate School of Science and Technology Policy

KAIST 과학기술정책대학원 <2025 대통령을 위한 열가지 과학 질문>

stp.kaist.ac.kr/media/view/i...

19.05.2025 05:23 👍 2 🔁 3 💬 0 📌 0

Awwww can't wait to meet Cannoli 😍😍🐶

06.05.2025 09:56 👍 1 🔁 0 💬 0 📌 0