# 3 questions

Published articles for 3 questions.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## 3 Questions: Neural transparency and the future of AI design

DevFeed: [3 Questions: Neural transparency and the future of AI design](<https://devfeed.tech/articles/3-questions-neural-transparency-and-the-future-of-ai-design-37938.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/3-questions-neural-transparency-and-future-of-ai-design-0715>)

Author: Media Lab

Published: 2026-07-15T20:25:00Z

Content type: article

Language: en

Sources: [MIT AI News](<https://devfeed.tech/sources/mit-ai-news.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [User Interfaces](<https://devfeed.tech/topics/user-interfaces.md>), [interface](<https://devfeed.tech/topics/interface.md>), [Language models](<https://devfeed.tech/topics/language-models.md>)

Tags: [3-questions](<https://devfeed.tech/tags/3-questions.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-companion](<https://devfeed.tech/tags/ai-companion.md>), [ai-empathy](<https://devfeed.tech/tags/ai-empathy.md>), [ai-hallucinations](<https://devfeed.tech/tags/ai-hallucinations.md>), [ai-personalization](<https://devfeed.tech/tags/ai-personalization.md>), [ai-safety](<https://devfeed.tech/tags/ai-safety.md>), [ai-sycophancy](<https://devfeed.tech/tags/ai-sycophancy.md>), [ai-toxicity](<https://devfeed.tech/tags/ai-toxicity.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [anthony-baez](<https://devfeed.tech/tags/anthony-baez.md>), [apps](<https://devfeed.tech/tags/apps.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [behavioral-prediction](<https://devfeed.tech/tags/behavioral-prediction.md>), [character-ai](<https://devfeed.tech/tags/character-ai.md>), [chatbot-behavior](<https://devfeed.tech/tags/chatbot-behavior.md>), [computer-science-and-technology](<https://devfeed.tech/tags/computer-science-and-technology.md>), [data](<https://devfeed.tech/tags/data.md>), [ethics](<https://devfeed.tech/tags/ethics.md>), [faculty](<https://devfeed.tech/tags/faculty.md>), [human-ai-interaction](<https://devfeed.tech/tags/human-ai-interaction.md>), [human-computer-interaction](<https://devfeed.tech/tags/human-computer-interaction.md>), [interface](<https://devfeed.tech/tags/interface.md>), [interview](<https://devfeed.tech/tags/interview.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mechanistic-interpretability](<https://devfeed.tech/tags/mechanistic-interpretability.md>), [media-lab](<https://devfeed.tech/tags/media-lab.md>), [mental-health](<https://devfeed.tech/tags/mental-health.md>), [mit-faculty-interview](<https://devfeed.tech/tags/mit-faculty-interview.md>), [mit-media-lab](<https://devfeed.tech/tags/mit-media-lab.md>), [neural](<https://devfeed.tech/tags/neural.md>), [neural-transparency](<https://devfeed.tech/tags/neural-transparency.md>), [pat-pataranutaporn](<https://devfeed.tech/tags/pat-pataranutaporn.md>), [persona-scores](<https://devfeed.tech/tags/persona-scores.md>), [persona-vectors](<https://devfeed.tech/tags/persona-vectors.md>), [personalized-ai](<https://devfeed.tech/tags/personalized-ai.md>), [research](<https://devfeed.tech/tags/research.md>), [safety](<https://devfeed.tech/tags/safety.md>), [school-of-architecture-and-planning](<https://devfeed.tech/tags/school-of-architecture-and-planning.md>), [sheer-karny](<https://devfeed.tech/tags/sheer-karny.md>), [sunburst-visualization](<https://devfeed.tech/tags/sunburst-visualization.md>), [technology-and-society](<https://devfeed.tech/tags/technology-and-society.md>), [transparency](<https://devfeed.tech/tags/transparency.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

An MIT Media Lab team introduces "neural transparency," an interface that visualizes internal patterns in AI models to help users anticipate how personalized chatbots may behave. The approach compares model activations associated with contrasting traits such as empathy, honesty, toxicity, hallucination, and sycophancy, then maps custom system prompts onto those behavior directions.

### Source excerpt

Assistant Professor Pat Pataranutaporn describes a new interface that lets everyday users glimpse inside an AI's neural network before their chatbot ever says a word.

## 3 Questions: Beyond data-driven aesthetics

DevFeed: [3 Questions: Beyond data-driven aesthetics](<https://devfeed.tech/articles/3-questions-beyond-data-driven-aesthetics-37937.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/3-questions-beyond-data-driven-aesthetics-alexandros-haridis-0629>)

Author: School of Architecture and Planning

Published: 2026-06-29T18:00:00Z

Content type: news

Language: en

Sources: [MIT AI News](<https://devfeed.tech/sources/mit-ai-news.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Data visualization](<https://devfeed.tech/topics/data-visualization.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>), [Mathematics](<https://devfeed.tech/topics/mathematics.md>), [Computer science](<https://devfeed.tech/topics/computer-science.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [3-questions](<https://devfeed.tech/tags/3-questions.md>), [aesthetic-judgment](<https://devfeed.tech/tags/aesthetic-judgment.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-and-aesthetics](<https://devfeed.tech/tags/ai-and-aesthetics.md>), [alexandros-haridis](<https://devfeed.tech/tags/alexandros-haridis.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [alumni-ae](<https://devfeed.tech/tags/alumni-ae.md>), [applied-arts](<https://devfeed.tech/tags/applied-arts.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [beyond-data-driven-aesthetics](<https://devfeed.tech/tags/beyond-data-driven-aesthetics.md>), [computational-aesthetics](<https://devfeed.tech/tags/computational-aesthetics.md>), [computer-science-and-technology](<https://devfeed.tech/tags/computer-science-and-technology.md>), [data](<https://devfeed.tech/tags/data.md>), [data-visualization](<https://devfeed.tech/tags/data-visualization.md>), [design](<https://devfeed.tech/tags/design.md>), [design-computation](<https://devfeed.tech/tags/design-computation.md>), [exhibits](<https://devfeed.tech/tags/exhibits.md>), [interactive-installations](<https://devfeed.tech/tags/interactive-installations.md>), [interview](<https://devfeed.tech/tags/interview.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mit-architecture](<https://devfeed.tech/tags/mit-architecture.md>), [mit-exhibits](<https://devfeed.tech/tags/mit-exhibits.md>), [mit-keller-gallery](<https://devfeed.tech/tags/mit-keller-gallery.md>), [mit-sa-plus-p](<https://devfeed.tech/tags/mit-sa-plus-p.md>), [philosophy](<https://devfeed.tech/tags/philosophy.md>), [research](<https://devfeed.tech/tags/research.md>), [school-of-architecture-and-planning](<https://devfeed.tech/tags/school-of-architecture-and-planning.md>), [shape-grammars](<https://devfeed.tech/tags/shape-grammars.md>), [special-events-and-guest-speakers](<https://devfeed.tech/tags/special-events-and-guest-speakers.md>)

### AI overview

An MIT Keller Gallery exhibition by Alexandros Haridis examines the history of aesthetic judgment and creative production in computing, connecting architecture, design computation, algorithms, and machine-learning systems.

### Source excerpt

In a new Keller Gallery exhibition, Alexandros Haridis SM '17, PhD '22 traces centuries of ideas about aesthetic judgment and explores how design can make complex computational systems visible.