ChatGPT is sometimes amazing, and sometimes hilariously wrong. Here, it confidently explains to me why an abacus is faster than a GPU. 😃

1/Large language models like Galactica and ChatGPT can spout nonsense in a confident, authoritative tone. This overconfidence - which reflects the data they’re trained on - makes them more likely to mislead.

6 AI websites to finish work faster: 1. Sheet+ - bit.ly/3Iq565o 2. DeepCode - bit.ly/3VPuZ1M 3. Akkio - bit.ly/3iau3r7 4. Autocode - bit.ly/3Z62ZJY 5. OpenAI Codex - bit.ly/3QjL26X 6. DeepOpinion - bit.ly/3icB3nl v/Pratham

Graduate school application

🔥🔥🔥

🌶️🌶️🌶️

📢New Paper Alert!!🚀 arxiv.org/abs/2304.03728 Does ChatGPT have the ability to check facts by itself?🤔 We designed a simple, few-shot, unified chain-of-thought prompting pipeline that can do: 🔹Fact-checking ✅ 🔹Stereotype detection 🚫 🔹Hate speech detection 🙅 (1/2)

Can language models help us do better search?🤔 🎉In #ACL2023 findings, we present EAR pipeline: 🎲sample multiple queries from LM 🎯rescore to select best query 🔍BM25 search 💪boost OpenQA accuracy to beat DPR/GAR arxiv: arxiv.org/abs/2305.17080 code: github.com/voidism/EAR

So I finally did what I promised 3mo ago – We wrote a reflection paper on using LLMs to replicate crowdsourcing pipelines, based on an assignment in our Human-Centered NLP course! arxiv.org/pdf/2307.10168… 20+ students implemented 7 crowd. pipelines from prior research & find… 1/

The Happiness Equation and How AI Solves For It We are all engaged in pursuing and attaining happiness. Our Founding Fathers went so far as to call it out in the Declaration of Independence. So, can happiness be engineered? Short answer: Yes. The happiness equations are a good

I hope everyone in Taiwan 🇹🇼 is okay after the earthquake. My thoughts are with everyone affected. ❤️

I entered the Harry Potter Lottery for $40 tickets on TodayTix! Tap here to enter: todaytix.com/nyc/shows/1370…

I entered the Sleep No More Lottery for $99 tickets on TodayTix! Tap here to enter: todaytix.com/nyc/shows/2138…

Students from the Soundability Lab will present 7 papers, posters, & demos at the upcoming #UIST2024 & #ASSETS2024 conferences. 🙌🎉 Come chat with us! Xinyun Cao, Alex, & I will attend UIST. Z. Jeremy Huang, Liang-Yuan (Leo) Wu, Xinyun Cao, & I will attend ASSETS. accessibility.eecs.umich.edu/#team

Unfortunately, I missed #ASSETS2024, but look out for Soundability Lab students Z. Jeremy Huang, Xinyun Cao, & Liang-Yuan (Leo) Wu presenting two papers, a poster, & a demo tomorrow. The key session is "3B: Sounds Around Us," 9 – 10:15 am. Details in the thread:

Finally, Liang-Yuan (Leo) Wu will present a poster on CARTGPT (3:30-4:15pm), a human-AI approach to generating highly accurate real-time captioning. Our approach uses LLMs & ASR to fix in-situ CART errors in edge situations (e.g., high noise, fast speakers). dl.acm.org/doi/10.1145/36…

Congrats Liang-Yuan (Leo) Wu for the #ASSETS2024 best poster award. 🎉

🥳 Huge congrats for the #ASSETS2024 🏆 Best Poster Award to Liang-Yuan Wu Liang-Yuan (Leo) Wu, Andrea Kleiver & Dhruv Jain Dhruv “DJ” Jain! CARTGPT is a human-#AI approach to generating highly accurate real-time captioning using LLMs & ASR to fix in-situ CART errors in edge situations

🥳 Huge congrats for the #ASSETS2024 Best Poster Award to Liang-Yuan Wu Liang-Yuan (Leo) Wu, Andrea Kleiver & Dhruv Jain Dhruv “DJ” Jain! CARTGPT is a human-#AI approach to generating highly accurate real-time captioning using #LLMs & ASR to fix in-situ CART errors in edge situations.

Looking forward to presenting our #CHI2025 work with Dhruv “DJ” Jain , jaylin herskovitz , Liang-Yuan (Leo) Wu , and Dr. Cecily Morrison on designing intent-driven AI systems for supporting deaf and hard of hearing people's sensemaking of auditory environments! Session Link: programs.sigchi.org/chi/2025/progr…