iiinova — where your digital self keeps evolving

Advait Bhat

@advaitmb.bsky.social

209 followers 364 following 9 posts

PhD student @uwcse.bsky.social ⁕ I work in HCI and NLP :) » advaitmb.com

Posts Replies Media

Advait Bhat @advaitmb.bsky.social · 16/04/2026

This paper would not have been possible without the collaboration and guidance of @mjakesch.bsky.social, @mariannealq.bsky.social and @informor.bsky.social. The paper is now available in open access! #chi2026 dl.acm.org/doi/10.1145/...

dl.acm.org

Reactive Writers: How Co-Writing with AI Changes How We Engage with Ideas | Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems

100

Advait Bhat @advaitmb.bsky.social · 16/04/2026

This is algorithmic agenda-setting at the moment of ideation. As Bernard Cohen wrote of the press in 1963: it may not tell people what to think, but it is stunningly successful in telling them what to think about. AI writing assistants may now do the same for writers.

111

Advait Bhat @advaitmb.bsky.social · 16/04/2026

Writers did adapt the suggestions they kept — rewording them, adding personal anecdotes, making them sound like their own. But the underlying framing and concepts from the AI survived into the final text, even in passages writers composed themselves.

100

Advait Bhat @advaitmb.bsky.social · 16/04/2026

Writers with a Positive AI ended up writing about different topics than writers with a Critical AI, and both wrote on a narrower range of topics than writers working alone.

110

Advait Bhat @advaitmb.bsky.social · 16/04/2026

Writers accepted or rejected suggestions based on whether they agreed with them, regardless of if they had come up with the ideas themselves. They felt in control as they could always reject or edit, but they didn't choose which ideas got surfaced in the first place.

100

Advait Bhat @advaitmb.bsky.social · 16/04/2026

What we saw: writers read AI suggestions before their own ideas had a chance to form. Ideation gave way to reading and evaluating. As one participant put it: "Well, now I'm not thinking about what I'm writing. I'm reading the sentence."

110

Advait Bhat @advaitmb.bsky.social · 16/04/2026

We analyzed 1,291 co-writing sessions and interviewed 19 participants who wrote an opinion text on a controversial topic. Some wrote with an AI assistant supportive of a position, some with an AI whose suggestions leaned critical, and some wrote on their own, without AI assistance.

100

Advait Bhat @advaitmb.bsky.social · 16/04/2026

Building on our earlier work showing AI suggestions can shift the attitudes writers hold, we asked: how does this happen? What changes in the writing process itself? bsky.app/profile/info...

100

Advait Bhat @advaitmb.bsky.social · 16/04/2026

How are AI tools changing our writing process? In our #chi2026 paper, we find a shift in the way writers write and engage with ideas: from generating ideas to reacting to the ones AI surfaces. We call it reactive writing.

174

Reposted by Advait Bhat

Kabir Ahuja @kabirahuja2431.bsky.social · 22/04/2025

📢 New Paper! Tired 😴 of reasoning benchmarks full of math & code? In our work we consider the problem of reasoning for plot holes in stories -- inconsistencies in a storyline that break the internal logic or rules of a story’s world 🌎 W @melaniesclar.bsky.social, and @tsvetshop.bsky.social 1/n

A screenshot of the first page of the paper, containing the paper title: Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection and the names of the authors: Kabir Ahuja, Melanie Sclar, and Yulia Tsvetkov. All the three authors are from CSE department in the University of Washington in Seattle, USA. They can be reached at {kahuja,msclar,yuliats}@cs.washington.edu

1104