Tootfinder

Two easy questions to keep in mind when considering using an LLM for anything, if you’re going to do that:
1. Does it matter if it’s wrong?
2. Is it useful to have examples of what’s typical?
Those two cut through a lot of noise.
/end

Counter Examples in Non-Archimedean Locally Convex Spaces
M. E. Egwe, J. A Braimah
https://arxiv.org/abs/2510.09626 https://arxiv.org/pdf/2510.09626…

Counter Examples in Non-Archimedean Locally Convex Spaces
In this paper, we shall consider some counter examples in non-archimedean locally convex spaces with special closed subspaces and Schauder basis in non-archimedean Fréchet spaces as well as closed subspaces \emph{without} Schauder basis in non-archimedean Fréchet spaces.

Checking out WebSocketStream in #dotnet 10. It definitely makes writing and reading WebSocket messages a bit simpler, giving you an experience similar to all other stream abstractions in #dotnet.

Again I'm confused at the human urge to pretend something is way more automated than it really is. Examples:
- Robot 'chef' that only automates the very least time-consuming part of cooking, serving no purpose but to slow things down: https://post.lurk.org/@jonty@chaos.soc

Fisher Matrix for Beginners
David Wittman (UC Davis)
https://arxiv.org/abs/2510.09683 https://arxiv.org/pdf/2510.09683

Fisher Matrix for Beginners
The Fisher information matrix is used widely in astronomy (and presumably other fields) to forecast the precision of future experiments while they are still in the design phase. Although many sources describe the mathematics of the formalism, few sources offer simple examples to help the beginner. This pedagogical document works through a few simple examples to develop conceptual understanding of the applications.

Advancing credibility and transparency in brain-to-image reconstruction research: Reanalysis of Koide-Majima, Nishimoto, and Majima https://arxiv.org/abs/2511.07960 by @… et al.;

Advancing credibility and transparency in brain-to-image reconstruction research: Reanalysis of Koide-Majima, Nishimoto, and Majima (Neural Networks, 2024)
A recent high-profile study by Koide-Majima et al. (2024) claimed a major advance in reconstructing visual imagery from brain activity using a novel variant of a generative AI-based method. However, our independent reanalysis reveals multiple methodological concerns that raise questions about the validity of their conclusions. Specifically, our evaluation demonstrates that: (1) the reconstruction results are biased by selective reporting of only the best-performing examples at multiple levels; …

Adversarial Attacks Leverage Interference Between Features in Superposition
Edward Stevinson, Lucas Prieto, Melih Barsbey, Tolga Birdal
https://arxiv.org/abs/2510.11709 https://…

Adversarial Attacks Leverage Interference Between Features in Superposition
Fundamental questions remain about when and why adversarial examples arise in neural networks, with competing views characterising them either as artifacts of the irregularities in the decision landscape or as products of sensitivity to non-robust input features. In this paper, we instead argue that adversarial vulnerability can stem from efficient information encoding in neural networks. Specifically, we show how superposition - where networks represent more features than they have dimensions …

Again I'm confused at the human urge to pretend something is way more automated than it really is. Examples:
- Robot 'chef' that only automates the very least time-consuming part of cooking, serving no purpose but to slow things down: https://post.lurk.org/@jonty@chaos.soc

Geodesic Calculus on Latent Spaces
Florine Hartwig, Josua Sassen, Juliane Braunsmann, Martin Rumpf, Benedikt Wirth
https://arxiv.org/abs/2510.09468 https://

Geodesic Calculus on Latent Spaces
Latent manifolds of autoencoders provide low-dimensional representations of data, which can be studied from a geometric perspective. We propose to describe these latent manifolds as implicit submanifolds of some ambient latent space. Based on this, we develop tools for a discrete Riemannian calculus approximating classical geometric operators. These tools are robust against inaccuracies of the implicit representation often occurring in practical examples. To obtain a suitable implicit represent…

Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors
Alexis Ross, Jacob Andreas
https://arxiv.org/abs/2510.11502 https://arxiv.org…

Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors
Research on reasoning in language models (LMs) predominantly focuses on improving the correctness of their outputs. But some important applications require modeling reasoning patterns that are incorrect. For example, automated systems that can reason about and simulate student errors are useful for providing real-time feedback in the classroom or offline practice for educators-in-training. This paper presents a new method, MISTAKE, that (1) constructs high-quality synthetic examples of reasonin…