Engineering Serendipity through Recommendations of Items with Atypical Aspects
Ramit Aditya, Razvan Bunescu, Smita Nannaware, Erfan Al-Hossami
https://arxiv.org/abs/2505.23580
Localized surface plasmons in a Weyl semimetal nanosphere
Francesco M. D. Pellegrino, Francesco Buccheri, G. G. N. Angilella
https://arxiv.org/abs/2505.23626
Solvated electrons in polar liquids as epsilon-near-zero materials tunable in the terahertz frequency range
Matthias Runge, Michael Woerner, Denys I. Bondar, Thomas Elsaesser
https://arxiv.org/abs/2505.22198
On the Role of Demagnetizing Tensors in Arbitrary Orientations of General Ellipsoid: Implications for MRI Safety Assessment
Tomppa Pakarinen
https://arxiv.org/abs/2505.21761
I'm not shocked that Musk would try to manipulate Grok to vent his opinions. We've seen his manipulation before in the twitter recommender system.
I am kind of fascinated by how difficult it is. I think that broadly trained LLMs tend to converge to the same "worldview", which is mostly left-libertarian.
You can't really force them away from this on one issue without introducing inconsistencies, and breaking the guardrails.
This https://arxiv.org/abs/2501.13863 has been replaced.
initial toot: https://mastoxiv.page/@arX…