Congrats to Advait Bhat | अद्वैत , whose paper, "Interacting with Next-Phrase Suggestions: How Suggestion Systems Aid and Influence the Cognitive Processes of Writing," received an Honorable Mention from ACM IUI 2026 '23. Read it here: bit.ly/3ZRgKvb #IUI2023 #GPT4 #ChatGPT #ACM #UI

Thank you so much, Daniel Buschek, for your kind words and this insightful thread 🙌 It's truly rewarding to know that our work resonated with you! Really excited to see how our field evolves and conversations around interaction with LLMs grow! #LLM #HCI

Wrote an article w/ Ziang Xiao about #IUI2023, highlighting several notable papers where researchers presented their work on the intersection of #HCI and #AI medium.com/human-centered…

We discuss the implications of our results and argue that opinions built into AI language technologies must be monitored and engineered more carefully. The paper (open access): bit.ly/LLM_influence Thanks to my collaborators Advait Bhat | अद्वैत, Daniel Buschek, Lior Zalmanson, & Mor Naaman (informor.bsky.social)! 6/6

Check out our latest paper on how opinionated language models can influence our writing and also (more strikingly) the opinions we hold! Catch the presentation tomorrow at #CHI2023

Our paper (dl.acm.org/doi/abs/10.114…) was mentioned in the MIT Technology Review !🕺

;_;

An article based on our recent work in the The Wall Street Journal !

Achievement unlocked lol, our paper was featured on Linus Tech Tips

This is so cool! Our paper was just covered in the CHI 2023 Editor's Choice Papers!🥳 @maurice_jks Daniel Buschek Lior Zalmanson Mor Naaman (informor.bsky.social) Thanks Werner Geyer for the shoutout! Our paper: Co-Writing with Opinionated Language Models Affects Users’ Views [bit.ly/LLM_influence]

It feels like AI is getting smarter every day—but what if it’s not just smarter, but sneakier? 🤖🧠 What if your AI assistant wasn’t just helping you, but subtly manipulating your decisions? 🤔 Here's what we found in our new study: arxiv.org/abs/2502.07663 [1/11] 🧵

Open-ended long-form conversations beyond mere "chitchat" remain a challenge for even the best language models. Check out Vidya Srinivas's work on coaching agents that reveals and resolves critical tensions in goal-oriented conversations.

We're doing it again! 🚨 Building a Resilient PM Career in a Stormy Job Market Last time had PMs & SPMs from Flipkart, PhonePe, EA, Udaan, 1Mg, Jiva. 🎀 Close knit (20 people max) 📅 Saturday 11AM (on Zoom) 🎟️ DM me if you want in Reactions from the last sesh below👇👇👇

📢 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/ Melanie Sclar, and tsvetshop 1/n

📢 Excited to present our poster at #ICLR2025! Agent S: An Open Agentic Framework that Uses Computers Like a Human. Come explore how Agent S leverages Experience Augmented Planning to interact with computers like humans do! 📍Hall 3 + Hall 2B, Poster #408 🗓️ April 26th, 10 AM

Many agents (Claude Code, Codex CLI) interact with the terminal to do valuable tasks, but do they currently work well enough to deploy en masse? We’re excited to introduce Terminal-Bench: An evaluation environment and benchmark for AI agents on real-world terminal tasks. Tl;dr

Congratulations to University of Washington #UWAllen Ph.D. grads Ashish Sharma & Sewon Min, Association for Computing Machinery Doctoral Dissertation Award honorees! Sharma won for #AI tools for mental health; Min received honorable mention for efficient, flexible language models. #ThisIsUW news.cs.washington.edu/2025/06/04/all…

Terminal-Bench and Warp Zach Lloyd in TechCrunch today :) (link in replies) I firmly believe that the future of LLM-Computer interaction is through something that looks like a terminal interface. Great to see this picking up steam.

I’m excited to share our new nature paper 📝, which provides strong evidence that the walkability of our built environment matters a great deal to our physical activity and health. Details in thread.🧵 nature.com/articles/s4158…