I am extremely excited about this work! It opens a new and useful way of using agents (addressing a new category of "FOMO" tasks). And, it's highly generalizable: monitor prices, paper pubs, GitHub, Discord -- even traffic cameras, all with a simple text prompt

Extremely excited to share this work with everyone -- we've been working on this since even before the Magentic One release last Fall. I'm also very glad to bring the Human back into the loop.

I am presenting tomorrow (Wednesday) my TOCHI Microsoft work “Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions” at ~11:55am in G301 :) should be fun 🥳 work done w/ @jennwv.bsky.social @qveraliao.bsky.social @adamfourney.bsky.social @gaganbansal.bsky.social 🤩

We’ve been working on this for quite a while. Super excited to share!

☀️New paper! Generative AI agents are powerful but complex—how do we design them for transparency and human control? 🤖✨ At the heart of this challenge is establishing common ground, a concept from human communication. We identify 12 key challenges in improving common ground between humans & agents.