←
Fluid Interfaces1,660 posts
Fluid Interfaces avatar

Fluid Interfaces

@FluidInterfaces

Building upon insights from psychology and neuroscience, the Fluid Interfaces group creates systems and interfaces for cognitive enhancement. @medialab @MIT

◷ Joined February 2012▧ 179 Photos and videos
Manuel Cherep avatar
⟳ Fluid Interfaces retweeted
Manuel Cherep@manuelcherep·Oct 8

The Workshop on Agent Behavior is tomorrow starting at 8:30 AM in Continental Ballroom 4! If you’re @COLM_conf come check it out. We have some amazing speakers giving very different perspectives on how to study agents.

✨Announcing the first Workshop on Agent Behavior @COLM_conf 2026 (Oct 9, San Francisco 🌅) aiagentbehavior.com/ We invite two types of contributions: (i) papers, and (ii) benchmark proposals. We are also seeking reviewers. More details below!

AHA | MIT Media Lab avatar
⟳ Fluid Interfaces retweeted
AHA | MIT Media Lab@AHA_MediaLab·Oct 7

Most AI benchmarks measure what models can do. ImpactBench measures what AI does to us. 800+ behavioral metrics. 48,540 conversations. Ten models. Undesirable behaviors avoided in only 53.1% of evaluations. Explore: impactbench.media.mit.edu

Post attachmentPost attachmentPost attachment
MIT Media Lab avatar
⟳ Fluid Interfaces retweeted
MIT Media Lab@medialab·Oct 5

Curious about applying to the Media Lab? Register for the Virtual Open House for Prospective Students on October 9! You’ll have an opportunity to hear from staff, faculty, and students; learn about the academic program and the research groups; and ask questions. Learn more and register for the webinar: media.mit.edu/events/2026-ma…

Manuel Cherep avatar
⟳ Fluid Interfaces retweeted
Manuel Cherep@manuelcherep·Sep 17

Last week, I was invited to present our @icmlconf 2026 paper “Visual Persuasion: What Influences Decisions of Vision-Language Models?” at the ECCV VisPer Workshop. We created a visual prompt optimization method (CVPO), in which we iteratively edit images (e.g., w/ @NanoBanana 🍌) to maximize the feedback given by VLM judges. While this method can be used for lots of applications, we use it to discover factors that persuade agents (and, as a proxy, people) while making decisions. More details and examples below! Work w/ Pranav M R*, @PattieMaes, and @nikhilsinghmus

0:26
Manuel Cherep avatar
⟳ Fluid Interfaces retweeted
Manuel Cherep@manuelcherep·Oct 6

I'm at COLM this week! If you're interested in chatting about AI agent vs human behavior, feel free to reach out :) I will also be on campus at Stanford (Oct 6-7) and Berkeley (Oct 8)

Cathy Fang avatar
⟳ Fluid Interfaces retweeted
Cathy Fang@thecatfangs·Sep 15

We got Best-in-Show at @ArsElectronica Expanded Conference! Echoing the gallery’s theme of “expanded play”, seeing the surprises and pure joy on people’s face when playing with our piece was the biggest reward. ars.electronica.art/negotiat…

Post attachmentPost attachment

In Plato's Allegory of the Cave, prisoners chained to a wall perceive only shadows—and mistake them for reality. We extend this concept: a shadow man, controlled by an LLM, exists in 2D and perceives only silhouettes. His singular goal is to turn off the light that defines his existence. Users place objects in his path; he kicks them away. The cycle repeats. This mirrors the perceptual limits of AI. An LLM cannot see—it reads descriptions of sight. It processes language about the world without directly accessing the world itself. The shadow man embodies this gap. Both are confined to representations. The piece is a meditation on AI as cave-dweller—processing patterns without grasping the higher-dimensional reality that casts them.

0:49
MIT Media Lab avatar
⟳ Fluid Interfaces retweeted
MIT Media Lab@medialab·Sep 14

Curious about applying to the Media Lab? Register for the Virtual Open House for Prospective Students on October 9! You’ll have an opportunity to hear from staff, faculty, and students; learn about the academic program and the research groups; and ask questions. Learn more and register for the webinar: media.mit.edu/events/2026-ma…

MIT Media Lab avatar
⟳ Fluid Interfaces retweeted
MIT Media Lab@medialab·Sep 4

In 1979, MIT researchers said "put that there" to a computer, and it listened. Yesterday, OpenAI launched GPT-6 Astra, the most powerful AI model ever built, opening with 47-year-old footage from our Media Room to show exactly where the idea came from. The premise that Richard Bolt, Chris Schmandt, and Eric Hulteen proved nearly five decades ago still holds: machines should adapt to human language, not the other way around. The best ideas don't expire...they compound. READ THE STORY: mitmedialab.info/4zTwbXb

Post attachment
AHA | MIT Media Lab avatar
⟳ Fluid Interfaces retweeted
AHA | MIT Media Lab@AHA_MediaLab·Aug 20

What's your real relationship with @claudeai ? Our AHA team collaborated with @AnthropicAI on Reflect, Claude's new beta feature that shows your AI habits and helps you stay aligned with your personal goals. Check your Claude settings (desktop) to explore your own patterns!

Post attachment
Cathy Fang avatar
⟳ Fluid Interfaces retweeted
Cathy Fang@thecatfangs·Aug 18

Do some AI models refuse more user requests than others? Are people using AI to generate illicit content more or less over time? And which models do people go to for coding vs role-play? Unfortunately, existing reports of AI use from frontier labs are coarse and proprietary that do not help us understand the impacts and natural uses of AI. This prompted us to create a public AI observatory ai-observatory.org/

1/ How are people really using AI? Today, researchers across @MIT, @Stanford, + 12 academic institutions are launching the Public AI Observatory: public infrastructure for measuring how people actually use AI assistants in the wild. 🔗 ai-observatory.org/ 📜 dataprovenance.org/ai_observ…

Post attachmentPost attachmentPost attachment
Nataliya Kosmyna, Ph.D avatar
⟳ Fluid Interfaces retweeted
Nataliya Kosmyna, Ph.D@nataliyakosmyna·Aug 13

Today we are excited to release the NeuroDatasets tool, where one can browse and find all available neuroscience datasets for all major modalities: EEG, MRI, MEG, NIRS, PET and more. Check the NeuroDatasets tool here: datasets.neuro2.ai

3:11
Fluid Interfaces avatar
Fluid Interfaces@FluidInterfaces·Aug 12

The device also provides reminders such as “Did you remember to turn off the stove?” While this kind of technology is in its early stages, a small study conducted last year by researchers at the MIT Media Lab confirmed improved performance of object finding among users”.

Fluid Interfaces avatar
Fluid Interfaces@FluidInterfaces·Aug 12

Using a multimodal large language model, MemPal creates a real-time automated text diary of actions and conversations between an individual and others. The technology allows users to ask questions like “Where is my phone?” or “Where is my wallet?”