InfoQ Homepage AI, ML & Data Engineering Content on InfoQ
-
NVIDIA Personal AI Router Distributes AI Tasks across Local Compute
NVIDIA Personal AI Router (PAIR), now available in beta, lets you combine the inference capacity of multiple computers on your local network and automatically distribute AI requests among them. It is primarily designed for local multi-agent AI workloads, where multiple independent model calls can otherwise overwhelm one GPU.
-
How LinkedIn Trains AI Job Search 8x Faster with Multi-Teacher Distillation
LinkedIn has published details of the training infrastructure behind its AI-powered job search, describing a multi-teacher distillation pipeline that compresses knowledge from large teacher models into a compact 0.6B-parameter ranking model.
-
Session Traces and Cost Controls Help Diagnose AI Agent Failures
Session traces and cost controls are emerging as key observability techniques for diagnosing AI agent failures, helping teams spot tool-call loops and runaway spend while preserving enough execution context for post-incident debugging.
-
OpenAI Releases GPT-6 Astra for Coding and Computer Use
OpenAI has released GPT-6 Astra, a new model focused on coding, computer use, long-running agentic tasks, and cybersecurity, with availability across ChatGPT, Codex, and the OpenAI API.
-
Meta's Recipe for Building Agents as "Organizational Second Brains"
Meta describes how an AI agent can be designed to capture the logic and expertise of domain experts, rather than simply storing documents or retrieving relevant information. The system, dubbed an "organizational second brain", was built for a specialized compliance domain, but Meta argues the architecture generalizes to areas like security, finance, engineering, and procurement.
-
GitLab Warns That AI Agent Sandboxes Are Only as Secure as Their Network Access
GitLab warns that isolating an AI coding agent in a sandbox does not necessarily make the agent safe. In a new security analysis, the company describes an internal evaluation in which an AI agent escaped its sandbox by exploiting a vulnerable package proxy that had been explicitly placed on the sandbox's allowlist.
-
Google Mantis: an Agentic Vulnerability Scanning Harness for Reducing False Positives
Google has open-sourced Mantis, an AI-agent framework designed to automate the software vulnerability lifecycle, from identifying and validating vulnerabilities to reproducing and fixing them. Google says it developed Mantis to address the high rate of false positives and hallucinated vulnerabilities produced by conventional AI-powered code scanning.
-
How Figma Uses AI Agents for Security
The engineering team at software company Figma recently documented how they built AI agents to help their security team investigate alerts, search past incidents, check company systems, and even prepare code fixes. The agents learn from previous investigations, reducing repetitive work and helping engineers resolve complex alerts about 70% faster.
-
Beyond Zero: Google Publishes Successor to BeyondCorp
In a recent research paper, Google introduced Beyond Zero, a “security model for the AI era” that extends Zero Trust to autonomous AI agents. The new approach moves access decisions from the application level to individual resources and actions, combining static authorization controls with dynamic AI-driven decisions to enable machine-speed enforcement for humans and agents.
-
Redefining GIS: Declarative Symbology and Collaborative Workflows in JupyterGIS
JupyterGIS is a GIS-focused extension for Jupyter notebooks. The recent 0.16 release enhances collaborative features, real-time editing, and support for large-scale data processing, including remote sensing. It introduces better visualisation tools and extends compatibility to R users. Community feedback highlights practical concerns and a desire for improved portability.
-
Copilot Code Review Reaches Azure Repos, Billed Per Review with Reporting Two Days behind
Microsoft opened GitHub Copilot code review for Azure Repos to all Azure DevOps customers, after acknowledging that many are not ready to migrate to GitHub. Reviews bill per use through the linked Azure subscription and appear in Cost Management 48 hours later. Budgets notify but do not stop reviews, and concurrency caps at five per organization.
-
Shopify Introduces Gisting: Compressing LLM System Prompts into Learned Tokens
Shopify's engineering introduced gisting, a novel technique for compressing long LLM prompts into a smaller set of learned "gist" tokens, improving throughput and reducing inference cost.
-
Cohere’s Parse 5 Promises Efficient Multi-Modal Information Extraction from Complex Documents
Cohere has launched Parse 5, a multimodal foundation model designed to extract structured data from complex enterprise documents. The 2.3-billion-parameter system converts visually rich PDFs into Markdown while providing bounding box coordinates for visual grounding. It has been evaluated against over 2,000 enterprise pages, achieving an average score of 79.2 in key performance areas.
-
Swiggy Uses 350+ Features and Multi-Task MLP to Predict Customer Lifetime Value
Swiggy developed an in-house predicted lifetime value model using more than 350 pre order features and a multi task MLP for Food and Instamart. Adding order count as an auxiliary task reduced model parameters by 63% while improving predictive performance. The pLTV signal is used with Google Target ROAS bidding to optimize customer acquisition.
-
Cloudflare Adds Optional OAuth Scopes, Letting Developers Mark What Users May Decline
Cloudflare has added optional OAuth scopes, letting client owners mark which permissions users may deselect at consent. The company names MCP servers as the motivating case, since agents request the union of everything they might do. Partial consent exists elsewhere, but developer control over which scopes are droppable does not.