iiinova — where your digital self keeps evolving

MIT Mathematics @mitmath.bsky.social · 02/03/2026

A team from MIT and UCSD including Assistant Professor Adityanarayanan "Adit" Radhakrishnan have devised a way to test whether LLMs hold hidden biases, moods, and abstract concepts, marking a major step towards creating models which are safe yet effective. news.mit.edu/2026/exposin... (MIT News)

news.mit.edu

Exposing biases, moods, personalities, and abstract concepts hidden in large language models

A new method can test whether a large language model contains hidden biases, personalities, moods, or other abstract concepts. MIT researchers can zero in on connections within a model that encode for...

030

MIT Mathematics @mitmath.bsky.social · 14/10/2025

Lauren K. Williams PhD ‘05 has been named a 2025 MacArthur Fellow for "significant contributions to numerous mathematical fields, including cluster algebras, representation theory, and algebraic geometry.” 👉 Read more via MIT Alumni: alum.mit.edu/slice/mit-al...

alum.mit.edu

MIT Alum Awarded 2025 MacArthur “Genius Grant”

MIT alumna and mathematician Lauren K. Williams PhD ’05 has won a 2025 MacArthur Fellowship.Read more.

291

MIT Mathematics @mitmath.bsky.social · 05/09/2025

By using a sparse autoencoder, Prof Berger and @bergerlab.bsky.social students uncover how protein language models make predictions."Identifying features that protein language models track has the potential to reveal novel biological insights from these representations." @mitscience.bsky.social

news.mit.edu

Researchers glimpse the inner workings of protein language models

MIT researchers used sparse autoencoders to shed light on the inner workings of protein language models, an advance that could streamline the process of identifying new drugs or vaccine targets.

051