TheoPhysEval: Assessing AI agents at autonomous theoretical physics problem solving https://arxiv.org/abs/2610.16733
arXiv.org
TheoPhysEval: Assessing AI agents at autonomous theoretical...
We present a suite of 50 unpublished research-level theoretical physics problems with verifiable answers. Without AI assistance, a typical problem in our collection could be solved by a world...
🔥1
A dataset of formalised theorem statements from the Annals of Mathematics https://arxiv.org/abs/2610.18301
arXiv.org
A dataset of formalised theorem statements from the Annals of Mathematics
Recent progress in autoformalisation of mathematics using AI has been impressive. Measuring this progress requires datasets of formal statements that are both hard and trustworthy. We present...
Magic state cultivation on a superconducting quantum processor https://www.science.org/doi/10.1126/science.aee7961
Science
Magic state cultivation on a superconducting quantum processor
Fault-tolerant quantum computing requires a universal gate set, but the necessary non-Clifford gates represent a significant resource cost for most quantum error correction architectures. Magic state cultivation offers an efficient alternative to ...
https://github.com/ethanwsussman/Yang--Mills-LLM-experiment
Please, we need to not incentivize rushing out 10,000-page slop
Proceeds to rushing out slop
GitHub
GitHub - ethanwsussman/Yang--Mills-LLM-experiment: Documents related to an attempt with Levent Alpoge to get Claude to finish Balaban's…
Documents related to an attempt with Levent Alpoge to get Claude to finish Balaban's program to construct Yang--Mills. (Under construction!) - ethanwsussman/Yang--Mills-LLM-experiment
SC♯: superconductivity intertwined with topological order https://arxiv.org/abs/2610.10679
arXiv.org
SC$^\sharp$: superconductivity intertwined with topological order
Superconductivity and intrinsic topological order can intertwine in ways that go beyond simple coexistence. Here we develop a classification framework for (2+1)D gapped superconductors with...
👾1
Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents https://arxiv.org/abs/2610.07447
arXiv.org
Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents
Autoresearch agents tackle open-ended problems by repeatedly proposing candidate solutions, evaluating them, and using feedback to guide subsequent experiments. We show that independent runs of...
Holographic theory of non-invertible gravitational anomalies https://arxiv.org/abs/2610.15358
arXiv.org
Holographic theory of non-invertible gravitational anomalies
We review a many-body formulation of gravitational anomalies as obstructions to realizing the complete low-energy data by a local {\it bosonic} lattice quantum system of the same dimension. In...
Quantum error correction well below the color code threshold https://cdn.prod.website-files.com/669960f53cd73aedb80c8eea/6ad6013f8ae0364b2cd03c53_c8c5526bc88434b2e47f6ffc3b27deca_Quantum-Error-Correction-Well-Below-the-Color-Code-Threshold.pdf
👾1
RuneBench Agent Benchmark on RuneScape Gameplay Tasks https://maxbittker.github.io/runebench/
maxbittker.github.io
runescape-bench: AI Agent Benchmark for RuneScape
runescape-bench evaluates AI coding agents on their ability to play RuneScape.
Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments https://arxiv.org/abs/2610.15634
arXiv.org
Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model...
Sycophancy in large language models risks amplifying unsupported claims or beliefs across the knowledge ecosystem as these systems increasingly contribute to research synthesis, evaluation, and...
How does Fable 5.1 hide messages in images?
https://www.lesswrong.com/posts/WHEQps5PK8LrrcTAb/how-does-fable-5-1-hide-messages-in-images
https://www.lesswrong.com/posts/WHEQps5PK8LrrcTAb/how-does-fable-5-1-hide-messages-in-images
Lesswrong
How does Fable 5.1 hide messages in images? — LessWrong
TL;DR
Frontier LLMs are now capable of generating artistic images using SVG. We ask – if these LLMs had to hide a message in an image – how would the…
Frontier LLMs are now capable of generating artistic images using SVG. We ask – if these LLMs had to hide a message in an image – how would the…
👀1
A Fix for Softmax and Cross-Entropy https://arxiv.org/abs/2610.31642
arXiv.org
A Fix for Softmax and Cross-Entropy
Standard implementations of softmax, log-softmax, and cross-entropy have two numerical bugs. The first bug, Softmax Collapse, rounds the target logit's gradient to zero if that one logit is much...
👍7🔥1🥴1