InfoQ Homepage AI, ML & Data Engineering Content on InfoQ
-
MySQL 9.6 Changes Foreign Key Constraints and Cascade Handling
MySQL is changing the way foreign key constraints and cascades are managed. Starting with MySQL 9.6, foreign key validation and cascade actions are handled by the SQL layer rather than the InnoDB storage engine. This will improve change tracking, replication accuracy, and data consistency, making MySQL more reliable for CDC pipelines, mixed-database environments, and analytics workloads.
-
Apple Researchers Introduce Ferret-UI Lite, an On-Device AI Model for Seeing and Controlling UIs
Apple's Ferret-UI Lite is a 3B-parameter model optimized for mobile and desktop screens, designed to interpret screen images, understand UI elements such as icons and text, and interact with apps by, e.g., reading messages, checking health data, and more.
-
AI "Vibe Coding" Threatens Open Source as Maintainers Face Crisis
Daniel Stenberg shut down cURL's bug bounty after AI submissions hit 20%. Mitchell Hashimoto banned AI code from Ghostty. Steve Ruiz closed all external PRs to tldraw. Economic research shows "vibe coding" weakens the user engagement that sustains open source. As developers delegate to AI agents, documentation visits and bug reports collapse—threatening the ecosystem's viability.
-
Rivet Launches the Sandbox Agent SDK to Solve Agent API Fragmentation
Rivet Sandbox Agent SDK provides a universal API for coding agents, allowing developers to work with different agent runtimes like Claude Code, Codex, OpenCode, and Amp without rewriting their integration for each one. It addresses the fragmentation across agent APIs, session handling, and streaming formats that has historically made agent integrations complex and difficult to maintain.
-
Databricks Introduces Lakebase, a PostgreSQL Database for AI Workloads
Databricks has recently announced the general availability of Lakebase, a serverless, PostgreSQL-based OLTP database that scales compute and storage independently. Lakebase is designed to integrate with the Databricks platform, providing a hybrid solution that combines both transactional and analytical capabilities.
-
OpenAI Introduces Harness Engineering: Codex Agents Power Large‑Scale Software Development
OpenAI introduces Harness Engineering, an AI-driven methodology where Codex agents generate, test, and deploy a million-line production system. The platform integrates observability, architectural constraints, and structured documentation to automate key software development workflows.
-
OpenAI Launches Frontier, a Platform to Build, Deploy, and Manage AI Agents across the Enterprise
OpenAI Frontier is an enterprise platform for building, deploying, and managing AI agents, designed to make AI agents reliable, scalable, and integrated into real company systems and workflows.
-
Hugging Face Introduces Community Evals for Transparent Model Benchmarking
Hugging Face has launched Community Evals, a feature that enables benchmark datasets on the Hub to host their own leaderboards and automatically collect evaluation results from model repositories.
-
GitHub Agentic Workflows Unleash AI-Driven Repository Automation
Recently launched in technical preview, GitHub Agentic Workflows introduce a way to automate complex, repetitive repository tasks using coding agents that understand context and intent, GitHub says. This enables workflows such as automatic issue triage and labeling, documentation updates, CI troubleshooting, test improvements, and reporting.
-
How Dropbox Built a Scalable Context Engine for Enterprise Knowledge Search
Dropbox engineers have detailed how the company built the context engine behind Dropbox Dash, revealing a shift toward index-based retrieval, knowledge graph-derived context, and continuous evaluation to support enterprise AI at scale.
-
Moonshot AI Releases Open-Weight Kimi K2.5 Model with Vision and Agent Swarm Capabilities
Moonshot AI released Kimi K2.5, their latest open-weight multimodal LLM. K2.5 excels at coding tasks, with benchmark scores comparable to frontier models such as GPT-5 and Gemini. It also features an agent swarm mode, which can direct up to 100 sub-agents for attacking problems with parallel workflow.
-
Leapwork Research Shows Why AI in Testing Still Depends on Reliability, Not Just Innovation
Leapwork recently released new research showing that while confidence in AI-driven software testing is growing rapidly, accuracy, stability, and ongoing manual effort remain decisive factors in how far teams are willing to trust automation.
-
Does AI Make the Agile Manifesto Obsolete?
Capgemini's Steve Jones argues AI agents building apps in hours have killed the Agile Manifesto, as its human-centric principles don't fit agentic SDLCs. While Forrester reports 95% still find Agile relevant, Kent Beck proposes "augmented coding" and AWS suggests "Intent Design" over sprint planning. The debate: Is Agile dead, or evolving for AI collaboration?
-
Agoda’s API Agent Converts Any API to MCP with Zero Code and Deployments
Agoda engineers developed API Agent, enabling a single MCP server to access any internal REST or GraphQL API with zero code and zero deployments. The system reduces overhead from multiple APIs, supports AI-assisted queries, and uses in-memory SQL post-processing for safe, scalable data handling across internal services.
-
Google Explores Scaling Principles for Multi-Agent Coordination
Google Research tried to answer the question of how to design agent systems for optimal performance by running a controlled evaluation of 180 agent configurations. From this, the team derived what they call the "first quantitative scaling principles for AI agent systems", showing that multi-agent coordination does not reliably improve results and can even reduce performance.