Actualités
The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents’ Inquiry Capability
arXiv:2509.24958v2 Announce Type: replace Abstract: An effective physician should possess a combination of empathy, expertise...
The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks
arXiv:2505.10507v1 Announce Type: new Abstract: Translation-based strategies for cross-lingual transfer XLT such as translate-train —...
The data center boom in the desert
In the high desert east of Reno, Nevada, construction crews are flattening the golden foothills...
The curious case of the disappearing Lamborghinis
When Sam Zahr first saw the gray Rolls-Royce Dawn convertible with orange interior and orange...
The Coverage Principle: How Pre-Training Enables Post-Training
arXiv:2510.15020v2 Announce Type: replace-cross Abstract: Language models demonstrate remarkable abilities when pre-trained on large text...
The Confidence Trap: Gender Bias and Predictive Certainty in LLMs
arXiv:2601.07806v1 Announce Type: new Abstract: The increased use of Large Language Models (LLMs) in sensitive...
The Complete Guide to Vector Databases for Machine Learning
Vector databases have become essential in most modern AI applications...
The Complete Guide to Pydantic for Python Developers
Python’s flexibility with data types is convenient when coding, but it can lead to runtime...
The Complete Guide to Inference Caching in LLMs
Calling a large language model API at scale is expensive and slow...
The Complete Guide to Data Augmentation for Machine Learning
Suppose you’ve built your machine learning model, run the experiments, and stared at the results...
The case for fixing everything
The handsome new book Maintenance: Of Everything, Part One, by the tech industry legend Stewart...
The case for embedding audit trails in AI systems before scaling
With more AI applications and agents going into production, enterprises need robust and auditable AI...
