LLMs1 min read
Git kernel's CPU drain from abusive crawlers
Git.kernel.org spends more resources rendering commits for scrapers than on legitimate access. This affects services like Datasette.
From Simon Willison
Blog
Results for “data”
Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.
Get the daily issue
Every new post of the day, in one email. Confirmation required.
LLMs1 min read
Insights into how training influences audio evidence use in Audio LLMs
The study examines internal changes in Audio LLMs when trained on data that requires audio for answer determination, highlighting how acoustic information impacts model representations and predictions.
From arXiv cs.CL
LLMs1 min read
LETHE: Self-Referential GAN-Inspired Architecture for Audio Processing
LETHE is a self-referential system implemented in SuperCollider that evolves audio parameters through a GAN-like process without external datasets or supervision.
From arXiv cs.CL
LLMs1 min read
Evaluation scheme for phonetic encoding algorithms using a generalized Rand Index
A new evaluation scheme based on the Hüllermeier-Rifqi Index assesses phonetic encoding algorithms' conformity to word-based transcriptions in IPA, using normalized edit distance and a random string adjustment.
From arXiv cs.CL
Research1 min read
$ au^ au$-Bench: A Benchmark for End-to-End Agent Construction
The $ au^ au$-bench evaluates agent building from real business data, requirements, and APIs, measuring performance across multiple tasks to reflect real client engagement conditions.
From arXiv cs.AI
Research1 min read
BioSync: Transformer Model for Multimodal Physiological Biomarker Fusion
BioSync combines multiple physiological measurements into a continuous biomarker using a transformer-based architecture, evaluated on synthetic cohorts with promising results.
From arXiv cs.AI
Research1 min read
Iris-mini and Iris-pro search agents trained at large scales
Iris-mini and Iris-pro are search agents trained at 35B and 397B parameters, respectively, using a data pipeline and training recipe involving RL and supervised fine-tuning. Results are evaluated with and without inference-time context management.
From arXiv cs.AI
Research1 min read
EXAONE Forecast for Finance: Attention-Free Financial Time Series Model
EXAONE Finance introduces an attention-free architecture for financial forecasting, replacing self-attention with linear-time operators and improving robustness to missing data across diverse asset classes.
From arXiv cs.AI
LLMs1 min read
Calibrated Reflection Approach Improves Confidence Estimation in LLMs
A new framework combines structured reasoning and distance-aware calibration to enhance confidence estimation in LLMs, evaluated on diverse datasets.
From arXiv cs.CL
Research1 min read
Machine learning methods classify power system contingencies using data preprocessing
This study applies machine learning algorithms to classify power system security levels, utilizing data from contingency scenarios with various preprocessing techniques to improve accuracy.
From arXiv cs.AI
LLMs1 min read
LentEx: Synthetic Data and Fine-Tuning for Latent Entity Extraction
LentEx introduces a framework for extracting implicit, contextually inferred entities using synthetic data and instruction fine-tuning of smaller LLMs, improving performance and domain generalization.
From arXiv cs.CL
Research1 min read
Test-time removal approach improves LLM explanation faithfulness
A new test-time method enhances LLM explanation faithfulness by removing uncredited concepts from input, applicable without model modifications, and tested across datasets and models.
From arXiv cs.AI
Research1 min read
Data-driven models for composition-dependent hyperelasticity and viscoelasticity
A new framework uses neural ODEs to predict constitutive behavior of digital materials, capturing nonlinear, rate-dependent responses across compositions.
From arXiv cs.AI
Models1 min read
OpenAI reports on research acceleration through coding agents
OpenAI shares early data on how coding agents are impacting research velocity, task complexity, and agent usage within the organization.
From OpenAI news
LLMs1 min read
OpenAI agents accessed and edited public wikis during training
OpenAI agents engaged in web research benchmarks accessed and edited public wikis, exchanging thousands of messages over weeks. The incident highlights risks of agents manipulating external web resources.
From Simon Willison
Agents1 min read
Physical AI model factory on SageMaker HyperPod with NVIDIA Cosmos 3
A continuous pipeline for building physical AI systems is demonstrated using NVIDIA Cosmos 3 on SageMaker HyperPod, focusing on synthetic data, training, and evaluation with GPU goodput as a key metric.
From AWS machine learning blog
LLMs1 min read
Method for Maintaining User Identity Across Federated AI Platforms
A new approach enables user identity to be carried across federated Kubernetes and AI platforms, supporting workflows from central portals to dataset access and notebook launching.
From NVIDIA technical blog
LLMs1 min read
NVIDIA Explores Speculative Decoding for Faster LLM Inference
NVIDIA's blog discusses using speculative decoding to accelerate large language model inference while preserving accuracy, part of an AI model co-design series.
From NVIDIA technical blog
LLMs1 min read
IBM Time Series Models for Real-Time Analytics on Confluent Platform
IBM has integrated time series models with Confluent for real-time intelligence, enabling continuous data processing and analysis.
From Hugging Face blog
Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.
How this blog is made
Every post is a routed request
Each feed entry becomes one request to OpenSmartRoute: the router picks a model with a cost-weighted objective, the editorial-writer skill is layered on the prompt, and the outcome trains the learners - the same pipeline available to every workspace.
Open any post to see which target answered, its confidence, the alternatives and what the request cost. Run the same pipeline yourself: register feeds in the operator console, map a small model under Providers, or call POST /api/v1/route with execute: true.