Anthropic's CEO admits the quiet part loud: we dont fully understand how AI works. They're building tools to decode it, like an MRI for AI, aiming for safety before it gets too powerful.
#AI #Interpretability #Anthropic
#interpretability
1 post1 participant0 posts today
Dario Amodei — The Urgency of Interpretability https://www.darioamodei.com/post/the-urgency-of-interpretability #AI #Anthropic #interpretability
New demo! Explore CLIP’s hidden concepts with SemanticLens.
Built on 16 SAEs from ViT Prisma (Check out https://github.com/soniajoseph/ViT-Prisma)
Try it: https://semanticlens.hhi-research-insights.eu
Paper: https://arxiv.org/pdf/2501.05398
Replied to Eric Maugendre
#AI #interpretability vs #explainability 
"The explanations themselves can be difficult to convey to nonexperts, such as end users and line-of-business teams" https://www.techtarget.com/searchenterpriseai/feature/Interpretability-vs-explainability-in-AI-and-machine-learning
Search Enterprise AIInterpretability vs. explainability in AI and machine learning | TechTargetLearn the key differences between interpretability and explainability in AI and machine learning, and explore examples, techniques and limitations.
Replied in thread
Replied in thread
"Feature importance helps in understanding which features contribute most to the prediction"
A few lines with #sklearn: https://mljourney.com/sklearn-linear-regression-feature-importance/
ML Journey · Sklearn Linear Regression Feature Importance - ML JourneyDiscover how to determine feature importance in linear regression models using Scikit-learn. This comprehensive guide covers methods like
Continued thread
"The following sections discuss several state-of-the-art interpretable and explainable #ML methods. The selection of works does not comprise an exhaustive survey of the literature. Instead, it is meant to illustrate the commonest properties and inductive biases behind interpretable models and [black-box] explanation methods using concrete instances."
https://wires.onlinelibrary.wiley.com/doi/full/10.1002/widm.1493#widm1493-sec-0010-title
Model "#interpretability and [black-box] #explainability, although not necessary in many straightforward applications, become instrumental when the problem definition is incomplete and in the presence of additional desiderata, such as trust, causality, or fairness."
https://wires.onlinelibrary.wiley.com/doi/full/10.1002/widm.1493
Heard I should write an #introduction? Ok.
Hi! I'm Jenn. I do research on #responsibleAI at Microsoft Research NYC. I'm in the FATE group and co-chair Microsoft's Aether working group on transparency.
My research background is in #machinelearning theory and algorithmic econ, but since my mid-career crisis I've focused on human-centered approaches to #transparency, #interpretability, & #fairness of AI.
I'm into #AI that augments, rather than replaces, human abilities.
www.jennwv.comJennifer Wortman Vaughan