@ellipsus_writes You have designed and built a really wonderful tool! I was just trying out Ellipsus and wondered who defined the pattern-counting algorithms. Did you handcraft them, or was gen AI involved?
Typical chatbots force co-writers to leave shared docs. Our #CHI2026 paper explores collaborative AI use in shared docs via 3 features:
🤖 Shared agent profiles
☑️ Repeatable tasks, triggered by users or system
💬 Agents respond in shared comments
Preprint in 🧵
w @flolehmann_de
@minsuk_chang I share the impression. You need tech expertise in the current job market. Companies develop their own models to reduce dependency on the big players. So, hands-on experience with models is a plus. For now. I could imagine that demand will rise for people who make models usable.
Finalising your #CHI2026 revision? Or suffering from not being allowed to do so? I've "reviewed-to-reject" one of our papers with ChatGPT, to show how this leads to bad reviews - and give ideas for responding to this: https://t.co/9mfaJfNQ6z
Excited to share StudyAlign, our new open-source project for conducting web-based user studies. I'll be presenting our work at #EICS2025 today. StudyAlign supports HCI researchers to streamline study setup and execution. Find our paper here: https://t.co/tZkBOufeul
We’ve redesigned mobile email replies - with & without AI. Tap sentences while reading to enter local responses (or get suggestions). Then connect them on a usual draft screen (or let AI do just that). Result: Flexible workflows with varying speed and control. #CHI2025 preprint👇
💡 Since it's #CHI writing season again, here are 10 practical tips on how to write better discussion sections: https://t.co/80MwK3qYHW
Spoiler: One of them is to start drafting early... ✍️
#HCI#CHI2025#CHI2024#AcademicTwitter
Many recent AI tools for text (#CHI2024👀) share a design trend: The page UI has been split into text snippets, cards, prompt boxes, etc.! ✂️My essay at #DIS2024 explores this fragmentation as "Collage" - to analyse & inform AI tool design. 📝 Preprint: https://t.co/eE3n7vjH0I
In "Writing and AI B", @KarimBenharrak Tim Zindulka @flolehmann_de@hen_drik@DBuschek created "Impressona", a text editor with a sidebar where you specify the details of a persona (e.g., a peer reviewer in this example) and then can get feedback (e.g., peer review!). #CHI2024
✍️Compelling writing is tailored to an audience but it's hard to ask them while writing. Can #LLMs help? 🤔
👉We explore this as "Writer-Defined #AI Personas for On-Demand Feedback Generation"
#CHI2024 preprint: https://t.co/cOe6LEET4T
@KarimBenharrak@flolehmann_de@hen_drik
📢 Last big update before #CHI2024: The #HCI + #AI preprint collection now lists about 280 papers! Incl. some workshop papers. Thank you all for sharing! 🤩
👉https://t.co/v3zYAXN4S9
📢 Looking for current research on #HCI + #AI? Here's a collection of 100+ #CHI2024 preprints, collected via arXiv and twitter. Suggestions welcome! https://t.co/zotnMajQkc
📢Join our 5th "HAI-GEN" workshop on Human-AI Co-Creation with Generative Models at @ACMIUI!
👉Submit a paper, demo or *poster* by Jan 16: https://t.co/h9zWF6tBEX
with @wernergeyer, Mary Lou Maher, Justin Weisz, @LydiaChilton#HAIGEN2024#CHI#HCI#AI#IUI2024
I wonder if @OpenAI had any German-speaking strategic consultancy before forming a partnership with @AxelSpringer. Bild is well known for low credibility and absurd headlines. welt has been criticized for misinformation lately.