Tootfinder

Imagine ChatGPT but instead of predicting text it just linked you to the to 3 documents most-influential on the probabilities that would have been used to predict that text.
Could even generate some info about which parts of each would have been combined how.
There would still be issues with how training data is sourced and filtered, but these could be solved by crawling normally respecting robots.txt and by paying filterers a fair wage with a more relaxed work schedule and mental health support.
The energy issues are mainly about wild future investment and wasteful query spam, not optimized present-day per-query usage.
Is this "just search?"
Yes, but it would have some advantages for a lot of use cases, mainly in synthesizing results across multiple documents and in leveraging a language model more fully to find relevant stuff.
When we talk about the harms of current corporate LLMs, the opportunity cost of NOT building things like this is part of that.
The equivalent for art would have been so amazing too! "Here are some artists that can do what you want, with examples pulled from their portfolios."
It would be a really cool coding assistant that I'd actually encourage my students to use (with some guidelines).
#AI #GenAI #LLMs

Walking in the #Schwarzwald :
More to come soon (Proudly served from my own Peertube instance without ads)
https://video.franzgraf.de/w/dGxHeu31jaak8fTrQoXHoX

😲 Antipsychotic-treated patients with schizophrenia see benefits from semaglutide, study claims
https://medicalxpress.com/news/2025-09-antipsychotic-patients-schizophrenia-benefits-semaglutide.html

Antipsychotic-treated patients with schizophrenia see benefits from semaglutide, study claims
A multicenter collaboration of Danish researchers reports that once-weekly semaglutide for 30 weeks lowered blood sugar levels and body weight and improved physical quality of life in antipsychotic-treated adults with schizophrenia and prediabetes.

In-Context Clustering with Large Language Models
Ying Wang, Mengye Ren, Andrew Gordon Wilson
https://arxiv.org/abs/2510.08466 https://arxiv.org/pdf/2510.08…

In-Context Clustering with Large Language Models
We propose In-Context Clustering (ICC), a flexible LLM-based procedure for clustering data from diverse distributions. Unlike traditional clustering algorithms constrained by predefined similarity measures, ICC flexibly captures complex relationships among inputs through an attention mechanism. We show that pretrained LLMs exhibit impressive zero-shot clustering capabilities on text-encoded numeric data, with attention matrices showing salient cluster patterns. Spectral clustering using attenti…

Rheinmetall baut bald auch Weltraumsatelliten
Der Rüstungskonzern Rheinmetall erweitert sein Portfolio um Weltraum-Satelliten. Dafür wurde ein Gemeinschaftsunternehmen mit der Firma Iceye gegründet.
https://www.

MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML
Haoyu Dong, Pengkun Zhang, Mingzhe Lu, Yanzhen Shen, Guolin Ke
https://arxiv.org/abs/2509.06806

MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML
Large language models (LLMs) possess broad world knowledge and strong general-purpose reasoning ability, yet they struggle to learn from many in-context examples on standard machine learning (ML) tasks, that is, to leverage many-shot demonstrations purely via in-context learning (ICL) without gradient descent. We introduce MachineLearningLM, a portable continued-pretraining framework that equips a general-purpose LLM with robust in-context ML capability while preserving its general knowledge an…

Enhanced Pebble Drift Across Planet-Opened Gaps in Windy Protoplanetary Disks
Lorraine Nicholson, Jaehan Bae
https://arxiv.org/abs/2510.07428 https://arxiv…

Enhanced Pebble Drift Across Planet-Opened Gaps in Windy Protoplanetary Disks
When a giant planet forms in a protoplanetary disks, it carves a gap around its orbit separating the disk into two parts: inner disk and outer disk. Traditional disk accretion models, which assume material transport is driven by viscosity, reveal that the planet-induced gap acts like a filter which blocks large dust grains from flowing into the inner disk. However, there is growing evidence that material transport may be driven by magnetically-driven winds instead. By carrying out a suite of tw…

Motion-Based User Identification across XR and Metaverse Applications by Deep Classification and Similarity Learning
Lukas Schach, Christian Rack, Ryan P. McMahan, Marc Erich Latoschik
https://arxiv.org/abs/2509.08539

Motion-Based User Identification across XR and Metaverse Applications by Deep Classification and Similarity Learning
This paper examines the generalization capacity of two state-of-the-art classification and similarity learning models in reliably identifying users based on their motions in various Extended Reality (XR) applications. We developed a novel dataset containing a wide range of motion data from 49 users in five different XR applications: four XR games with distinct tasks and action patterns, and an additional social XR application with no predefined task sets. The dataset is used to evaluate the per…

Understanding JWST water spectra: what can thermochemical models tell us about the (cold) water in protoplanetary disks?
Marissa Vlasblom, Milou Temmink, Andrew D. Sellek, Ewine F. van Dishoeck
https://arxiv.org/abs/2509.06494

Understanding JWST water spectra: what can thermochemical models tell us about the (cold) water in protoplanetary disks?
(Abridged) Rotational H$_2$O spectra as observed with JWST/MIRI provide a good probe of the temperature and column density structure of the inner disk. H$_2$O emission can also be influenced by dynamical processes, such as dust grains drifting inwards and their icy mantles sublimating once they cross the snowlines, thus enriching the inner regions in H$_2$O vapor. Recent work has found that this process may leave an imprint in the H$_2$O spectrum in the form of excess flux in the cold H$_2$O li…

Hydrodynamical Simulations of Planet Rebound Migration in Photo-evaporating Disks
Beibei Liu, Cl\'ement Baruteau, Zhaohuan Zhu, Ya-Ping Li, Sijme-Jan Paardekooper
https://arxiv.org/abs/2509.06695

Hydrodynamical Simulations of Planet Rebound Migration in Photo-evaporating Disks
This study investigates the orbital migration of a planet located near the truncated edge of protoplanetary disks, induced by X-ray photo-evaporation originating from the central star. The combined effects of turbulent viscous accretion and stellar X-ray photo-evaporation give rise to the formation of a cavity in the central few astronomical units in disks. Once the cavity is formed, the outer disk experiences rapid mass loss and the cavity expands inside out. We have conducted 2D hydrodynamica…