The daily ledger

llm 0.32.1

Release: llm 0.32.1 Fresh installs of LLM stopped working the other day because the OpenAI Python library dropped its usage of httpx, and it turned out LLM depended on that library but only installed it via a transitive…

An AI tool for prioritizing candidate biomarkers from wearable sensor data

Generative AI

llm-openrouter 0.7

Release: llm-openrouter 0.7 Now that this plugin is compatible with LLM 0.32 it can display the reasoning traces for LLMs available through OpenRouter. Updated for compatibility with LLM 0.32. Models now use…

Stop Making TUIs

Stop Making TUIs Thomas Ptacek advocates for building real native user interfaces for even the smallest of personal tools, because coding agents have reduced the cost of getting a usable-enough GUI up and running to…

Quoting Matt Webb

After I released version 1.0, I figured I would have to do the rotations myself. So I sat down with ChatGPT and I didn’t get it to write the code, but I got it to educate me. With a patient, interactive tutor, I was…

How mobility gives language models a deeper understanding of place

Algorithms & Theory

Measuring benchmark optimization in speech recognition

How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code

The mRNA cancer vaccine finally delivers

PLUS: Spirit Airlines' data turns into bidding war

OpenAI Adds Controls That Should've Been There Already

The new AI security controls follow the Hugging Face incident last month, though experts say many of these additions should have been in place prior to the frontier models escaping.

Hugging Face Journal Club: Training AI Scientists to Replicate Research

The Hugging Face research team discusses the Faraday-27B model that was post-trained to develop scientific reasoning to replicate AI papers, a key step towards full automation of AI R&D. Link to the paper:…

Slack turns coding into a group project

PLUS: Sell a high-value AI workflow audit as a consultant

Designing Human-mediated AI Guidance: Ready Together for Personalized Family Emergency Preparedness

arXiv:2608.19950v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are increasingly used across domains to provide personalized information, recommendations, and decision support. However, in some…

Socioduality: A Relational Process Framework for Human-AI Interaction

arXiv:2608.11322v2 Announce Type: replace-cross Abstract: Human-AI research often evaluates individual capabilities, joint performance, or final outputs, but these approaches can lose the interaction process that…

Improving Requirements Classification with SMOTE-Tomek Preprocessing

arXiv:2501.06491v4 Announce Type: replace-cross Abstract: This study emphasizes the domain of requirements engineering by applying the SMOTE-Tomek preprocessing technique, combined with stratified K-fold…

ReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance

arXiv:2608.19974v1 Announce Type: new Abstract: LLM agents in financial markets may cite rules yet still submit orders that violate executable constraints or misread surveillance evidence. We introduce ReguSim, a…

MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection

arXiv:2608.19901v1 Announce Type: cross Abstract: Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a direct distribution…

Interaction valence reveals contrasting social networks in dairy cattle

arXiv:2608.19222v1 Announce Type: new Abstract: Social relationships shape access to resources, exposure to conflict and group stability, yet automated livestock monitoring typically treats behaviour as isolated events.…

DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing

arXiv:2608.20161v1 Announce Type: new Abstract: Instruction-based image editing uses a planner-renderer pipeline: a vision-language model (VLM) first converts the instruction into an edit plan, and a diffusion model…

FMT$^{\mathrm{X}}$: Lazy Wavefront Search for Dynamic Replanning

arXiv:2509.08521v2 Announce Type: replace-cross Abstract: FMT$^{*}$ plans efficiently in static worlds by expanding a cost-ordered wavefront and collision-checking lazily, but its single-pass unvisited rule cannot…