Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A developer has added migration and refactoring skills to the Polylith tooling for Python, enabling AI agents to convert legacy single-repo projects into an agent-friendly Polylith Monorepo. The skills automate steps suc…
OpenAI and Thrive Holdings built a tax-preparation AI agent that cut document processing time by a third while achieving up to 97% accuracy. The system then self-improved over six weeks, raising the rate of fully accurat…
A perceptron, the simplest neural network, was introduced by Frank Rosenblatt in 1958. This article demonstrates building a perceptron from scratch in Python to classify numbers as positive or negative, showing how it le…
Engineering career outcomes and infrastructure observability decisions now rely on the same causal attribution methods, according to a cross-domain analysis. Staff+ promotion committees demand Difference-in-Differences o…
Anthropic reported degraded performance affecting multiple AI models on its platform. The company is offering email and text message notifications for users to track updates on the incident. Users must verify their phone…
Researchers analyzing token consumption in LLM-based multi-agent software engineering systems found that code review stages consume the majority of tokens at 59.4%, with input tokens accounting for 53.9% of total usage. …
Researchers introduced Gaia2, a benchmark for evaluating large language model agents in dynamic, asynchronous environments where scenarios evolve independently of agent actions. Testing of state-of-the-art models reveale…
Ernest Chan presented Conditional Portfolio Optimization (CPO), a machine-learning method that trains a neural network to predict portfolio performance based on market features and then solves a constrained optimization …
A developer found that deploying a 70B Llama model with RAG features caused time-to-first-token (TTFT) to jump from 180 ms to 1.4 seconds, as the model recomputed identical attention states for repeated 6,000-token conte…
OpenAI’s GPT models and Meta’s LLaMA-family use transformer architectures that convert text into token IDs, then map each ID to a dense vector via an embedding matrix. These vectors are combined with positional encodings…
A developer built a Quantified-Self RAG (Retrieval-Augmented Generation) system that ingests a decade of personal medical records from messy PDF scans using Unstructured.io, Sentence-Transformers, and Qdrant. The pipelin…
Developer Anil Madhavapeddy released TESSERA v1.1 and GeoTessera 0.9, improving temporal embeddings and S3+Zarr support, while also advancing io-uring libraries for OCaml. The updates address performance issues and expan…
A speculative proposal argues that training massively overparameterized neural networks with extremely high learning rates on small, diverse datasets could trigger a "catapulting" effect, producing human-like generalizat…
SimTooReal, a platform for robotics teams, now enables live telemetry and failure diagnosis for training runs in Isaac Lab, MuJoCo, Gazebo, and LeRobot with a single command. The tool wraps existing training scripts to s…
Overworld released Waypoint-1.5, an update to its generative world model that produces real-time environments at up to 720p and 60 frames per second on consumer hardware. The release introduces two model tiers — a 720p v…
A developer built a three-tier content quality ladder for programmatic directory sites, using a single `model_used` column to track content origin across three sites launched in April. The system prioritizes Claude Haiku…
A new machine learning paradigm treats relational databases as graphs, enabling graph neural networks to learn directly from the raw schema without manual feature engineering. The approach, detailed in a 2023 paper by Fe…
A new analysis of metastable states in transformer activation spaces confirms that token representations cluster into metastable groups across layers in trained models, as predicted by a recent dynamical systems theory, …
In an experiment on Gemma-2-2B's residual stream, researchers found that transformers store long-range contextual information in a compact, low-dimensional subspace of roughly 31 directions, rather than spreading it acro…
A developer found that improving data quality through feature engineering boosted a Logistic Regression model's accuracy from 72% to 86%—a 14-percentage-point gain—without changing the algorithm. By handling missing valu…