Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Khronos Group presented an open standards roadmap at SIGGRAPH ASIA 2025 in Hong Kong, December 15-18, covering cross-platform ML inferencing acceleration, glTF Gaussian Splats, and OpenXR Spatial Entities. The Machine Le…
Azure Databricks provides a production-grade feature engineering pipeline for MLOps using Apache Spark, Delta Lake, and MLflow. The pipeline follows the Medallion Architecture with Bronze, Silver, and Gold layers to tran…
A hospitalized individual is seeking collaborators for a machine learning project on Sudokus, aiming to build a dataset and eventually create an independent organization. The person is currently without a laptop but want…
A joint investigation by Consumer Reports, the Groundwork Collaborative and More Perfect Union found that Instacart used an AI pricing platform called Eversight to charge different customers different prices for the same…
A developer built rustnn, a Rust implementation of the W3C WebNN specification for Firefox, using Claude Code to accelerate development. The project implements 95 operators and validates against WPT conformance tests, wi…
Five AI models, a lookup table, and a human football fan predicted 72 World Cup group-stage fixtures. Claude Sonnet 4.6 won with 67 points, while GPT-5.5 tied the human at 52 points, and the simple Ranking Bot beat both.…
Microsoft shipped nine Azure Developer CLI releases in May and June 2026, adding a new tool command group, multi-layer provisioning with dependsOn, and a Rust MCP Server template for Azure Container Apps. The updates pos…
Researchers reverse-engineered the Apple Neural Engine (ANE), documenting its architecture, programming interface, and performance across A11-A18 and M1-M5 chips. The study reveals a direct user-space route to the ANE, t…
Microsoft's Visual Studio 2026 June update introduces three AI agents—Debugger, Profiler, and Cloud—that autonomously execute code, validate bugs, profile performance, and open pull requests, marking a shift from AI that…
A developer rebuilt their AI agent architecture from OpenClaw to Norax, achieving a cost reduction from $8-12/day to $1.80/day and implementing 11,000+ canonical memories with entity graph retrieval. The project evolved …
An AI agent developer implemented a sleep consolidation system to manage memory stores that grow to tens of thousands of items, causing retrieval slowdowns and irrelevant memories. The system merges similar memories, pru…
Norax builds an entity graph from its memory store to improve retrieval for AI agents. The graph uses entity extraction, co-occurrence edges, community detection, and weighted edges to capture relationships between conce…
Safi Shamsi released Graphify, an open-source skill that builds queryable knowledge graphs from multi-modal codebases for AI coding assistants like Claude Code and OpenAI Codex. The tool combines Tree-sitter static analy…
A developer built an artist attribution system using PyTorch and a pretrained ResNet-50 model. The system classifies paintings by artist with top-3 predictions, leveraging transfer learning for efficient training. The pr…
Norax developed a multi-signal memory architecture for AI agents that combines exact term matching, dense vector similarity, temporal decay, and entity graph reranking. The system outperforms single-signal retrieval by 4…
A developer built a RAG system from scratch using pgvector and Gemini embeddings, explaining design decisions such as choosing pgvector over dedicated vector databases, using 768-dimensional embeddings, and employing dif…
A developer built a cryptographically verifiable agent behavior system that produces tamper-proof receipts proving an AI agent followed approved rules. The demo uses standard hashing and signatures to catch rule swaps, e…
A new framework called 'belief webs' is proposed to unify beliefs, goals, and actions in intelligent agents, drawing from active inference, agent foundations, and machine learning. The framework addresses internal incons…
A developer built an AI agent using active inference that becomes curious on its own by minimizing surprise rather than chasing rewards. On a foraging task, the agent achieved 100% success by checking a hint before actin…
Shridhar Shah, a senior software engineer at Outshift by Cisco, built two AI agents to test theory of mind using the Sally-Anne false-belief test. One agent, which only tracks reality, fails the test like a toddler, whil…