🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Interested in PL+HCI? Want feedback on your work from a wholesome, enthusiastic community? Submit to PLATEAU! 2024.plateau-workshop.org ⏲️ Deadline: Dec. 6 📄 Submissions: 4–10 pages 🤝 Accepted papers get matched with PL+HCI mentors for detailed feedback! RTs appreciated! <3

LOVE this idea!!

🎉New Preprint! 🎉 Shreya Shankar led this investigation of challenges in aligning LLM outputs: *people* don't always have clear criteria, and these "squishy" criteria also drift as users tweak prompts + evaluate outputs. Human input critical in guiding co-evolution of prompts & evals!

[2] Prompting for Discovery: Flexible Sense-Making for AI Art-Making with Dreamsheets, presented by sh1m and J.D. Zamfirescu, asks how interfaces can better support artists in prompt-space explorations for text-to-image models.

"Rambler", a tool developed by Susan Lin Jeremy Warner J.D. Zamfirescu et al. provide a tool that converts your spoken rambling into coherent, written text! The "semantic zoom" tool lets you slide through versions of Full, 50%, 25%, and 10% length. This is the #CHI2024 tool I most need...

I think in the future, I will refuse to review papers that involve synthetic agents. I just can't take it seriously. If your goal is to simulate human behavior with "LLM agents" to automate out humans, count me out. There's much better things you could be doing with your time.

This is really cool new feature we've been working on Can you automatically improve/build LLM evaluators based on observing human feedback? Now live in LangSmith! Inspired by a lot of Shreya Shankar's great work

autoblocks Our technique, which we're calling ALIGN... Automated LLM-as-a-judge Improvement Guided by Notable Feedback ...was heavily inspired by the work of Shreya Shankar, J.D. Zamfirescu, Bjoern Hartmann, Aditya Parameswaran, and Ian Arawjo in their paper: arxiv.org/pdf/2404.12272…

Hmm, a journey that delves, you say?

Can we have more control over our social media feeds? Help researchers explore new solutions and receive $20 in compensation if you qualify and complete the study. Take the survey to see if you qualify: stanforduniversity.qualtrics.com/jfe/form/SV_e3…

this is high culture of my people

Paraphrasing from David Barstow's super motivating UC Berkeley EPIC Lab keynote: As computer scientists, "is the work you're doing supporting the world of truth? Or is it supporting the world of lies?"

Paper link: arxiv.org/abs/2404.12272 J.D. Zamfirescu and Ian Arawjo will also be around!!

Please retweet: I am recruiting PhD students at Berkeley! Please apply to UC Berkeley EECS or UC Joint Computational Precision Health Program if you are interested in ML applied to health, inequality, or social science, and mention my name in your app. More details on work/how to apply: cs.cornell.edu/~emmapierson/

📈Top cited articles from the last two years of ACM CHI (ACM CHI Conference) – the premier publication venue for HCI ("Human-Computer Interaction") research. What do you notice?

Tovi Grossman ACM CHI Conference I notice that J.D. Zamfirescu and Majeed Kazemitabaar are awesome.

This paper is cool. I like the idea. I'm quite disappointed that it wasn't submitted for traditional peer review. It sidesteps a crucial scientific process. It reflects poorly on the AI Safety community when OpenAI expresses concerns about xrisk and behaves this way.

"What AI Engineers Can Learn From Qualitative Research Methods in HCI" —a blog post: ianarawjo.medium.com/what-ai-engine…

Does the public think AIs are sentient? 🤖🧠 Our paper with the first US representative survey on digital minds, AI, Morality, and Sentience (AIMS), was accepted to #CHI2025. We find that 20% of U.S. adults believe some current AIs are already sentient, and 37% are not sure! 🧵

the best definition I have for "slop" is "low information density." I think we should not conflate it with other adjectives like "mundane," "verbose," "tasteless," or "hasty"