Maneesh Agrawala
@magrawala.bsky.social
Forest Baskett Professor of Computer Science and Director of the Brown Institute for Media Innovation at Stanford.
http://graphics.stanford.edu/~maneesh
http://graphics.stanford.edu/~maneesh
Pinned
Maneesh Agrawala
@magrawala.bsky.social
· Nov 14
Unpredictable Black Boxes are Terrible Interfaces
Why generative AI tools can be so difficult to use and how we might improve them
magrawala.substack.com
Earlier this year I wrote a substack post explaining why I think Generative AI tools are amazing and also incredibly frustrating to use:
magrawala.substack.com/p/unpredicta...
magrawala.substack.com/p/unpredicta...
MoVer is a Motion Verification DSL that can check if an LLM-generated motion graphics animation match your text prompts!
@jiajuma.bsky.social presented this work at SIGGRAPH 2025 making it easier for designers to specify and verify complex animations.
Paper, code and dataset: mover-dsl.github.io
@jiajuma.bsky.social presented this work at SIGGRAPH 2025 making it easier for designers to specify and verify complex animations.
Paper, code and dataset: mover-dsl.github.io
August 27, 2025 at 6:20 PM
MoVer is a Motion Verification DSL that can check if an LLM-generated motion graphics animation match your text prompts!
@jiajuma.bsky.social presented this work at SIGGRAPH 2025 making it easier for designers to specify and verify complex animations.
Paper, code and dataset: mover-dsl.github.io
@jiajuma.bsky.social presented this work at SIGGRAPH 2025 making it easier for designers to specify and verify complex animations.
Paper, code and dataset: mover-dsl.github.io
Oof -- still learning to post proper links on Bluesky.
Artists often explore designs, undoing and redoing parts of a sketch to try different ideas. Lvmin Zhang's PaintsAlter (presented at SIGGRAPH 2025) is a tool designed to facilitate such exploration
Updated link: lllyasviel.github.io/paints_alter...
w/ Chuan Yan, Yuwei Guo and Jinbo Xing
Updated link: lllyasviel.github.io/paints_alter...
w/ Chuan Yan, Yuwei Guo and Jinbo Xing
August 26, 2025 at 8:41 PM
Oof -- still learning to post proper links on Bluesky.
Artists often explore designs, undoing and redoing parts of a sketch to try different ideas. Lvmin Zhang's PaintsAlter (presented at SIGGRAPH 2025) is a tool designed to facilitate such exploration
Updated link: lllyasviel.github.io/paints_alter...
w/ Chuan Yan, Yuwei Guo and Jinbo Xing
Updated link: lllyasviel.github.io/paints_alter...
w/ Chuan Yan, Yuwei Guo and Jinbo Xing
August 26, 2025 at 8:32 PM
Artists often explore designs, undoing and redoing parts of a sketch to try different ideas. Lvmin Zhang's PaintsAlter (presented at SIGGRAPH 2025) is a tool designed to facilitate such exploration
Updated link: lllyasviel.github.io/paints_alter...
w/ Chuan Yan, Yuwei Guo and Jinbo Xing
Updated link: lllyasviel.github.io/paints_alter...
w/ Chuan Yan, Yuwei Guo and Jinbo Xing
Artists often explore possible designs, undoing and redoing parts of a sketch to try different ideas. Lvmin Zhang's PaintsAlter (presented at SIGGRAPH 2025) is a tool designed to facilitate such exploration
Paper and code: lllyasviel.github.io/paints_alter...
w/ Chuan Yan, Yuwei Geo and Jinbo Xing
Paper and code: lllyasviel.github.io/paints_alter...
w/ Chuan Yan, Yuwei Geo and Jinbo Xing
August 26, 2025 at 5:20 PM
Artists often explore possible designs, undoing and redoing parts of a sketch to try different ideas. Lvmin Zhang's PaintsAlter (presented at SIGGRAPH 2025) is a tool designed to facilitate such exploration
Paper and code: lllyasviel.github.io/paints_alter...
w/ Chuan Yan, Yuwei Geo and Jinbo Xing
Paper and code: lllyasviel.github.io/paints_alter...
w/ Chuan Yan, Yuwei Geo and Jinbo Xing
If you need to segment sketches into objects, Mia Tang has the tool for you. Enables re-composing the sketch after drawing. She presented her work on InkLayer at SIGGRAPH 2025.
Code, data and paper are here: inklayer.github.io
w/ @yaelvinker.bsky.social Chuan Yan, Lvmin Zhang
Code, data and paper are here: inklayer.github.io
w/ @yaelvinker.bsky.social Chuan Yan, Lvmin Zhang
August 25, 2025 at 6:48 PM
If you need to segment sketches into objects, Mia Tang has the tool for you. Enables re-composing the sketch after drawing. She presented her work on InkLayer at SIGGRAPH 2025.
Code, data and paper are here: inklayer.github.io
w/ @yaelvinker.bsky.social Chuan Yan, Lvmin Zhang
Code, data and paper are here: inklayer.github.io
w/ @yaelvinker.bsky.social Chuan Yan, Lvmin Zhang
Reposted by Maneesh Agrawala
Now that school is starting for lots of folks, it's time for a new release of Speech and Language Processing! Jim and I added all sorts of material for the August 2025 release! With slides to match! Check it out here: web.stanford.edu/~jurafsky/sl...
Speech and Language Processing
Speech and Language Processing
web.stanford.edu
August 24, 2025 at 7:28 PM
Now that school is starting for lots of folks, it's time for a new release of Speech and Language Processing! Jim and I added all sorts of material for the August 2025 release! With slides to match! Check it out here: web.stanford.edu/~jurafsky/sl...
Was recently introduced to Brian Marick's Oddly Influenced podcast. It's an amazing mix of ideas connecting software engineering, cognitive psychology and history of science.
Highly recommended! Has significantly extended my to-read list.
podcasts.apple.com/us/podcast/o...
Highly recommended! Has significantly extended my to-read list.
podcasts.apple.com/us/podcast/o...
Oddly Influenced
Technology Podcast · A podcast about how people have applied ideas from outside software to software.
podcasts.apple.com
August 20, 2025 at 9:40 PM
Was recently introduced to Brian Marick's Oddly Influenced podcast. It's an amazing mix of ideas connecting software engineering, cognitive psychology and history of science.
Highly recommended! Has significantly extended my to-read list.
podcasts.apple.com/us/podcast/o...
Highly recommended! Has significantly extended my to-read list.
podcasts.apple.com/us/podcast/o...
Looking forward to this workshop!
I'm very excited to announce our #SIGGRAPH2025 workshop:
Drawing & Sketching: Art, Psychology, and Computer Graphics 🎨🧠🫖
🔗 lines-and-minds.github.io
📅 Sunday, August 10th
Join us to explore how people draw, how machines draw, and how the two might draw together! 🤖✍️
Drawing & Sketching: Art, Psychology, and Computer Graphics 🎨🧠🫖
🔗 lines-and-minds.github.io
📅 Sunday, August 10th
Join us to explore how people draw, how machines draw, and how the two might draw together! 🤖✍️
July 24, 2025 at 4:40 AM
Looking forward to this workshop!
Reposted by Maneesh Agrawala
This is a good article and I completely agree with its argument for comprehensible research.
How can we reform science? I have some ideas. But I am not sure you’ll like them, because they don’t promise much. elevanth.org/blog/2025/07...
Which Kind of Science Reform
What hope is there for science reform, if we can't agree on what to reform? Right now, principles are more important than practices.
elevanth.org
July 21, 2025 at 10:58 PM
This is a good article and I completely agree with its argument for comprehensible research.
Reposted by Maneesh Agrawala
For context, AlphaFold is great, but is not a magic wand for making new drugs. (But Hassabis's latest claims go far beyond the hype that accompanied AlphaFold at the time.)
www.prospectmagazine.co.uk/ideas/techno...
www.prospectmagazine.co.uk/ideas/techno...
DeepMind has predicted the shape of every protein known to science. How excited should we be?
The AI-based breakthrough, like the sequencing of the human genome, may not turbocharge the development of new drugs as some hope. But as a resource f...
www.prospectmagazine.co.uk
July 5, 2025 at 10:23 AM
For context, AlphaFold is great, but is not a magic wand for making new drugs. (But Hassabis's latest claims go far beyond the hype that accompanied AlphaFold at the time.)
www.prospectmagazine.co.uk/ideas/techno...
www.prospectmagazine.co.uk/ideas/techno...
Reposted by Maneesh Agrawala
The AI for Content Creation workshop is kicking off today at #CVPR2025 - Grand Ballroom A1 - @magrawala.bsky.social Kai Zhang (Adobe), Charles Herrmann (Google), Mark Boss (Stability AI), Yutong Bai (UC Berkeley), Cherry Zhao (Adobe), Ishan Misra (Meta) and @jonbarron.bsky.social ! See you soon!
June 12, 2025 at 1:45 PM
The AI for Content Creation workshop is kicking off today at #CVPR2025 - Grand Ballroom A1 - @magrawala.bsky.social Kai Zhang (Adobe), Charles Herrmann (Google), Mark Boss (Stability AI), Yutong Bai (UC Berkeley), Cherry Zhao (Adobe), Ishan Misra (Meta) and @jonbarron.bsky.social ! See you soon!
At CVPR in Nashville for the Workshop on AI for Content Creation. I'll be speaking at 9am tomorrow 6/12.
ai4cc.net
ai4cc.net
AI for Content Creation Workshop
ai4cc.net
June 11, 2025 at 9:11 PM
At CVPR in Nashville for the Workshop on AI for Content Creation. I'll be speaking at 9am tomorrow 6/12.
ai4cc.net
ai4cc.net
There’s still time! If you are in Toronto I’d love to see you
Get your tickets and join us + @uoftmscac.bsky.social for an upcoming #DataSciencesSpeakerSeries talk: "Unpredictable Black Boxes are Terrible Interfaces" w/ Prof. @magrawala.bsky.social from @stanforduniversity.bsky.social
🗓️April 14
📷Info & reg: datasciences.utoronto.ca/event/prof-m...
🗓️April 14
📷Info & reg: datasciences.utoronto.ca/event/prof-m...
April 13, 2025 at 3:49 PM
There’s still time! If you are in Toronto I’d love to see you
Reposted by Maneesh Agrawala
Join DSI and @uoftmscac.bsky.social for an upcoming #DataSciencesSpeakerSeries talk: "Unpredictable Black Boxes are Terrible Interfaces" w/ Prof. @magrawala.bsky.social from @stanforduniversity.bsky.social
🗓️Friday, April 14
🔗Info & reg: datasciences.utoronto.ca/event/prof-m...
🗓️Friday, April 14
🔗Info & reg: datasciences.utoronto.ca/event/prof-m...
March 26, 2025 at 8:26 PM
Join DSI and @uoftmscac.bsky.social for an upcoming #DataSciencesSpeakerSeries talk: "Unpredictable Black Boxes are Terrible Interfaces" w/ Prof. @magrawala.bsky.social from @stanforduniversity.bsky.social
🗓️Friday, April 14
🔗Info & reg: datasciences.utoronto.ca/event/prof-m...
🗓️Friday, April 14
🔗Info & reg: datasciences.utoronto.ca/event/prof-m...
Reposted by Maneesh Agrawala
What will be the linchpin for AI dominance?
Read our NSF/OSTP recommendations written with Goodfire's Tom McGrath tommcgrath.github.io, Transluce's Sarah Schwettmann cogconfluence.com, MIT's Dylan Hadfield-Menell @dhadfieldmenell.bsky.social
TLDR; Dominance comes from **interpretability** 🧵 ↘️
Read our NSF/OSTP recommendations written with Goodfire's Tom McGrath tommcgrath.github.io, Transluce's Sarah Schwettmann cogconfluence.com, MIT's Dylan Hadfield-Menell @dhadfieldmenell.bsky.social
TLDR; Dominance comes from **interpretability** 🧵 ↘️
March 16, 2025 at 1:57 PM
What will be the linchpin for AI dominance?
Read our NSF/OSTP recommendations written with Goodfire's Tom McGrath tommcgrath.github.io, Transluce's Sarah Schwettmann cogconfluence.com, MIT's Dylan Hadfield-Menell @dhadfieldmenell.bsky.social
TLDR; Dominance comes from **interpretability** 🧵 ↘️
Read our NSF/OSTP recommendations written with Goodfire's Tom McGrath tommcgrath.github.io, Transluce's Sarah Schwettmann cogconfluence.com, MIT's Dylan Hadfield-Menell @dhadfieldmenell.bsky.social
TLDR; Dominance comes from **interpretability** 🧵 ↘️
Looking forward to giving a connected pair of upcoming talks!
Apr 14: I'll present Unpredictable Black Boxes are Terrible Interfaces for the Data Science Institute in Toronto
datasciences.utoronto.ca/event/prof-m...
Apr 14: I'll present Unpredictable Black Boxes are Terrible Interfaces for the Data Science Institute in Toronto
datasciences.utoronto.ca/event/prof-m...
Unpredictable Black Boxes are Terrible Interfaces - Prof. Maneesh Agrawala - DSI
Join us for the Inequity Speaker Series with Associate Professor Dustin Duncan, from the Department of Epidemiology and Co-Director of the Social and Spatial Epidemiology Unit, Columbia University.
datasciences.utoronto.ca
March 21, 2025 at 6:17 PM
Looking forward to giving a connected pair of upcoming talks!
Apr 14: I'll present Unpredictable Black Boxes are Terrible Interfaces for the Data Science Institute in Toronto
datasciences.utoronto.ca/event/prof-m...
Apr 14: I'll present Unpredictable Black Boxes are Terrible Interfaces for the Data Science Institute in Toronto
datasciences.utoronto.ca/event/prof-m...
Ran into this great article on Navigating Nostalgia from Jonathan Bean. It's about nostalgia for older techniology and interfaces, and it make a lovely reference to LineDrive maps.
Navigating Nostalgia: Technology, Intention, and the Road Ahead | IX Magazine Issue XXXII.2 March - April 2025
I recently took a road trip from Tucson, Arizona, to Portland, Oregon, to spend time with family and to spare our spoiled dog the indignity of flying in the cargo hold. I ended up...
interactions.acm.org
March 20, 2025 at 6:16 PM
Ran into this great article on Navigating Nostalgia from Jonathan Bean. It's about nostalgia for older techniology and interfaces, and it make a lovely reference to LineDrive maps.
In Barbados for the Bellairs workshop on computer animation!
February 22, 2025 at 12:53 PM
In Barbados for the Bellairs workshop on computer animation!
Reposted by Maneesh Agrawala
Hello Bluesky! 🔵 We start our account by having our third guess for Ask Me Anything session #3DV2025AMA!
Noah Snavely @snavely.bsky.social from Cornell & Google DeepMind! 🌟
🕒 You have now 24 HOURS to ask him anything — drop your questions in the comments below!
Keep it engaging but respectful!
Noah Snavely @snavely.bsky.social from Cornell & Google DeepMind! 🌟
🕒 You have now 24 HOURS to ask him anything — drop your questions in the comments below!
Keep it engaging but respectful!
November 26, 2024 at 3:33 PM
Hello Bluesky! 🔵 We start our account by having our third guess for Ask Me Anything session #3DV2025AMA!
Noah Snavely @snavely.bsky.social from Cornell & Google DeepMind! 🌟
🕒 You have now 24 HOURS to ask him anything — drop your questions in the comments below!
Keep it engaging but respectful!
Noah Snavely @snavely.bsky.social from Cornell & Google DeepMind! 🌟
🕒 You have now 24 HOURS to ask him anything — drop your questions in the comments below!
Keep it engaging but respectful!
Reposted by Maneesh Agrawala
Reposted by Maneesh Agrawala
3/ Domain-specific visualizations. A pair of pictures should say it all. What do you think the left picture is about? How about the right one? (Hint: they're the "same picture", yet obviously they're not. A lot more to say here!) ↵
April 21, 2024 at 2:33 PM
3/ Domain-specific visualizations. A pair of pictures should say it all. What do you think the left picture is about? How about the right one? (Hint: they're the "same picture", yet obviously they're not. A lot more to say here!) ↵
Thinking of adding this paper to my HCI Foundations and Frontiers course: arxiv.org/abs/2402.19194
So many questions though -- what was the IRB process like? how did NSF reimburse for the cannabis? ...
So many questions though -- what was the IRB process like? how did NSF reimburse for the cannabis? ...
High Expectations: An Observational Study of Programming and...
Anecdotal evidence of cannabis use by professional programmers abounds. Recent studies have found that some professionals regularly use cannabis while programming even for work-related tasks....
arxiv.org
March 20, 2024 at 5:58 PM
Thinking of adding this paper to my HCI Foundations and Frontiers course: arxiv.org/abs/2402.19194
So many questions though -- what was the IRB process like? how did NSF reimburse for the cannabis? ...
So many questions though -- what was the IRB process like? how did NSF reimburse for the cannabis? ...
Reposted by Maneesh Agrawala
Check out our paper for details on the cognitive gaps, mental models, and human theory of mind of LLMs and recommendations for designers. Thanks to my amazing coauthors - @magrawala.bsky.social, Roy Pea, Chris Pondoc, Colleen Seifert
t.co/QmZEKpwyhZ
t.co/QmZEKpwyhZ
Bridging the Gulf of Envisioning: Cognitive Design Challenges in...
Large language models (LLMs) exhibit dynamic capabilities and appear to comprehend complex and ambiguous natural language prompts. However, calibrating LLM interactions is challenging for...
t.co
March 20, 2024 at 4:53 PM
Check out our paper for details on the cognitive gaps, mental models, and human theory of mind of LLMs and recommendations for designers. Thanks to my amazing coauthors - @magrawala.bsky.social, Roy Pea, Chris Pondoc, Colleen Seifert
t.co/QmZEKpwyhZ
t.co/QmZEKpwyhZ
I'll be speaking at Univ. of Toronto's Data Science Institute next Mon Mar 25. You can still register!
datasciences.utoronto.ca/event/prof-m...
www.eventbrite.ca/e/unpredicta...
datasciences.utoronto.ca/event/prof-m...
www.eventbrite.ca/e/unpredicta...
Unpredictable Black Boxes are Terrible Interfaces– Prof. Maneesh Agrawala
Data Sciences Speaker Series with Prof. Maneesh Agrawala
www.eventbrite.ca
March 19, 2024 at 2:54 PM
I'll be speaking at Univ. of Toronto's Data Science Institute next Mon Mar 25. You can still register!
datasciences.utoronto.ca/event/prof-m...
www.eventbrite.ca/e/unpredicta...
datasciences.utoronto.ca/event/prof-m...
www.eventbrite.ca/e/unpredicta...
Reposted by Maneesh Agrawala
New work from my lab looking at ways to engage with teachers and students early on the machine learning development process to build AI powered education technology. We will present this work at CSCW2024.
hai.stanford.edu/news/data-ce...
hai.stanford.edu/news/data-ce...
A Data-Centered Approach to Education AI
Useful models need better data. Stanford scholars explore a path to ensure domain experts have more fruitful conversation.
hai.stanford.edu
March 1, 2024 at 2:11 AM
New work from my lab looking at ways to engage with teachers and students early on the machine learning development process to build AI powered education technology. We will present this work at CSCW2024.
hai.stanford.edu/news/data-ce...
hai.stanford.edu/news/data-ce...