iiinova — where your digital self keeps evolving

Sheshera Mysore @msheshera.bsky.social · 04/11/2025

I’m at #EMNLP2025 in Suzhou, China presenting this work! Get in touch if you'll be around and are free to catch up or meet!

001

Sheshera Mysore @msheshera.bsky.social · 27/06/2025

This was a deeply fulfilling collaboration at the Office of Applied Research at Microsoft with Debarati Das, Hancheng Cao, and Bahar Sarrafzadeh. 📄 Paper: arxiv.org/abs/2505.16023 📝 Blog (4-min read): prototypical-hai-collaborations.github.io 💻 GitHub: github.com/microsoft/pr...

github.com

GitHub - microsoft/prototypical-hai-collaborations: Repo accompanying the paper "Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild"

Repo accompanying the paper "Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild" - microsoft/prototypical-hai-collaborations

000

Sheshera Mysore @msheshera.bsky.social · 27/06/2025

🧭What this means for LLM alignment 🧭 Most excitingly, we found LLMs being used as partners in 🧠learning🧠. Aligning LLMs for learning represents a big opportunity for interdisciplinary work and our paper describes this and other under-explored research to explore in future.

Broad directions of future work implied by out findings.

100

Sheshera Mysore @msheshera.bsky.social · 27/06/2025

💎 What we found 💎 Eight PATHs explained 80-85% of the follow-up behaviors. And more interestingly, we found correlations between specific writing intents and PATHs. See the examples ⬇️

Example conversations showing correlated intents and follow-ups.

100

Sheshera Mysore @msheshera.bsky.social · 27/06/2025

🔦 What we did 🔦 1️⃣ We clustered users' follow-ups and identified a small set of clusters that represent prototypical human-AI collaboration behaviors, we call these PATHs. 2️⃣ We examined if PATHs vary by users’ intents, e.g. differing behavior in writing an email vs a story.

100

Sheshera Mysore @msheshera.bsky.social · 27/06/2025

🤔 We know what people are using LLMs for, but do we know how they collaborate with an LLM? 🔍 In a recent paper we answered this by analyzing multi-turn sessions in 21 million Microsoft Copilot for consumers and WildChat interaction logs: arxiv.org/abs/2505.16023

Overview of the key questions, data, and idea driving our analysis.

121

Sheshera Mysore @msheshera.bsky.social · 27/06/2025

💎 What we found 💎 Eight PATHs explained 80-85% of the follow-up behaviors. And more interestingly, we found correlations between specific writing intents and PATHs. See some examples ⬇️

Example conversations showing correlated follow-ups and writing intents.

000

Sheshera Mysore @msheshera.bsky.social · 27/06/2025

100

Reposted by Sheshera Mysore

Naomi Saphra @nsaphra.bsky.social · 26/04/2025

I wrote something up for AI people who want to get into bluesky and either couldn't assemble an exciting feed or gave up doomscrolling when their Following feed switched to talking politics 24/7.

nsaphra.net

The AI Researcher's Guide to a Non-Boring Bluesky Feed | Naomi Saphra

How to migrate to bsky without a boring feed.

2336094

Reposted by Sheshera Mysore

John Warner @biblioracle.bsky.social · 19/04/2025

IMO, the most important piece on AI of the last 6 months and I recommend it to everyone. A genuinely careful consideration of the technology and its intersections with culture and labor from @randomwalker.bsky.social and @sayash.bsky.social Authors of AI Snake Oil substack.com/home/post/p-...

substack.com

AI as Normal Technology

A new paper that we will expand into our next book

410226

Reposted by Sheshera Mysore

Reuters Institute @reutersinstitute.bsky.social · 18/04/2025

"We need this to be a real debate, and not two disconnected conversations talking past each other" AI expert David Caswell on the need to bridge the fault line emerging in debates about AI and the future of news reutersinstitute.politics.ox.ac.uk/news/we-need...

reutersinstitute.politics.ox.ac.uk

We need to bridge the fault line emerging in debates about AI and the future of news

“We need this to become a real debate, and not two disconnected conversations talking past each other,” argues AI expert David Caswell in this essay.

183

Reposted by Sheshera Mysore

Dan Goldstein @dggoldst.bsky.social · 18/12/2024

Microsoft's New Future of Work Report 2024 is out! More than 50 of us contributed to this! If you like hot, fresh citations about AI & productivity, you'll find hundreds here: aka.ms/nfw2024

aka.ms

Microsoft New Future of Work Report 2024 - Microsoft Research

As Microsoft approaches its 50th anniversary, the landscape of work continues to evolve at an unprecedented pace. The past year has marked a pivotal shift, moving from predictions and controlled lab s...

02810

Sheshera Mysore @msheshera.bsky.social · 29/11/2024

If you receive citations to multiple of your favorite authors you can get inundated with hundreds of emails a week at random times in the week which you then ignore. This script de-duplicates papers in your alerts, sorts them, and emails you a digest email! Give it a go!

010

Sheshera Mysore @msheshera.bsky.social · 29/11/2024

Okay friends, do you use Google Scholar Alerts to keep up with new papers but find the alert emails too overwhelming? If yes, then this is for you! I wrote a script you can run in GMail to create a regular digest for your Google Scholar Alerts: github.com/MSheshera/go...

120

Reposted by Sheshera Mysore

brendan o’connor @brenocon.bsky.social · 19/11/2024

We're hiring new #nlp faculty this year! Asst or Assoc Professors in NLP at UMass CICS -- careers.umass.edu/amherst/en-u...

careers.umass.edu

Details - Assistant/Associate Professor - Natural Language Processing (NLP) | Human Resources | UMass Amherst

16634

Sheshera Mysore @msheshera.bsky.social · 14/11/2024

I'm in Miami for #EMNLP2024! Come catch up with me or talk to me about: • personalization, interactive models • postdocs at Microsoft • the academic job market! • my paper about using calibrated retrievers for personalizing generation: aclanthology.org/2024.customn... (cross posting from X :P)

010