←
Martin Wattenberg733 posts
Martin Wattenberg avatar

Martin Wattenberg

@wattenberg

Human/AI interaction. Visualization as design, science, art. Professor at Harvard, and part-time at Google's People+AI Research initiative.

◷ Joined July 2008▧ 84 Photos and videos
Martin Wattenberg avatar
Martin Wattenberg@wattenberg·12 May 2023

Language models have some beautiful spiral plots reflecting positional patterns. And a vision model has heads that arrange images according to brightness and hues. But there’s a lot more to find! What else can you see?

Post attachment
David Bau avatar
⟳ Martin Wattenberg retweeted
David Bau@davidbau·21 Dec 2022

I want to show the NSF there would be broad support+utility for a "National Deep Inference" service for >100b LLMs. If your research would be enabled by an inference service on open LLMs w API access+overrides to internal activations, params, gradients: Please Like this thread!

Harvard SEAS avatar
⟳ Martin Wattenberg retweeted
Harvard SEAS@hseas·30 Nov 2022

Students explore the aesthetics of computing in new computer science course at SEAS. "CS73: Code, Data, and Art" is co-taught by @wattenberg and @viegasf, and teaches students how to create abstract art and communicate data sets through visualizations. buff.ly/3GXpkTE

Post attachment
Martin Wattenberg avatar
Martin Wattenberg@wattenberg·16 Nov 2022

Thinking about grad school next year? Interested in visualization, machine learning interpretability, or human/AI interaction? Consider Harvard. @viegasf and I are continuing to build our lab!

Post attachment
Martin Wattenberg avatar
Martin Wattenberg@wattenberg·21 Sep 2022

I'm teaching with @OpenProcessing 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!

Martin Wattenberg avatar
Martin Wattenberg@wattenberg·15 Sep 2022

The project is a systematic study of how a neural network represents more features than it has neurons, under a variety of conditions. (Oh, and I can't tweet without a typo, apparently. That's @AnthropicAI of course!)

Martin Wattenberg avatar
Martin Wattenberg@wattenberg·15 Sep 2022

Tiny neural networks have a surprisingly rich inner life, and may hold clues to how their larger cousins work. This image: evolution of feature vectors during learning. Full story: transformer-circuits.pub/202… (in collaboration with the great interpretability team at @AnthopicAI)

Post attachment
Golan Levin avatar
⟳ Martin Wattenberg retweeted
Golan Levin@golan·23 Aug 2022

SMASHOMANCY is a "divination system for cracked phone screens" and @djbaskin retains pole position as one of my favorite living creatives.

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.

Post attachmentPost attachmentPost attachmentPost attachment
Martin Wattenberg avatar
Martin Wattenberg@wattenberg·28 Jul 2022

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...