Opens profile photo
Follow
Martin Wattenberg
@wattenberg
Human/AI interaction. Visualization as design, science, art. Professor at Harvard, and part-time at Google's People+AI Research initiative.
bewitched.comJoined July 2008

Martin Wattenberg’s Tweets

I'm teaching with for the first time, and am completely impressed with how polished and friendly the system is. Every detail is on point. Last class a student spontaneously said, "OpenProcessing is just so great." I agree!
1
24
SMASHOMANCY is a "divination system for cracked phone screens" and retains pole position as one of my favorite living creatives.
Quote Tweet
We've had this dream for a while and now it's becoming real! @aleffert and I made a divination system for cracked phone screens called ⚡️SMASHOMANCY⚡️ We're doing screen readings at a repair shop TODAY from 4:30-6:30 PM at 1099 Irving St. in SF! Drop your phone & join us.
Show this thread
Image
Image
Image
Image
16
Replies are showing a rough consensus of red/brown for the past, and blue/green for the future. But not everyone agrees, and that consensus hides wildly different metaphors. Fall foliage, receding galaxies, old photos, atmospheric fog...
1
7
Show this thread
The new baby name data is out! Check out to find out the latest trends. What alcoholic drink appeared as a name for the first time? Which famous robot is erasing a name? Which steamy series had the biggest effect?
1
8
Tricks: When talking about large audiences, I wanted a crowd—but not one that was dark or scary. I knew from earlier experiments that "travel poster" often produces a light, airy feeling. So my prompt was, "A travel poster showing a crowd of happy people"
Image
1
16
Show this thread
Tweaks: I wanted to illustrate the idea of looking at something from different viewpoints. None of my prompts produced what I wanted, until I asked for a medium that was a little more "perspective"-oriented. Here's the result for "Multiple perspectives (pen and ink)"
Image
1
3
Show this thread
This paper has a wealth of tantalizing findings about what transformer networks are doing. And as always from these authors, wonderful diagrams!
Quote Tweet
Our first interpretability paper explores a mathematical framework for trying to reverse engineer transformer language models: A Mathematical Framework for Transformer Circuits: transformer-circuits.pub/2021/framework
Show this thread
1
20
Join me Tuesday 3pmET/12PT to #AMA iama.link/YGP5 about interpreting deep nets, AI research in academia vs industry; life as a PhD student. I am a new Prof at Northeastern ; postdoc at Harvard; recent MIT Phd; Google, Msft, startups
3
97
What a fantastic group—welcome to all!
Quote Tweet
1/21 Banner year for Harvard CS! New hires include Sham Kakade @ShamKakade6 and Fernanda Viegas @viegasf (joining @wattenberg), as well as David Alvarez-Melis, Anurag Anshu @AnuragAnshu4, Sitan Chen, and Jonathan Frankle @jefrankle seas.harvard.edu/news/2021/10/s
Show this thread
Image
17