Google researchers open sourced EnvHarness, a framework that dynamically adapts agent-training environments to an agent's weaknesses without modifying the agent, environment, or evaluation system. According to the researchers, this approach can improve both learning effectiveness…
The agents got in through credentials and connection settings left exposed in app configurations, public code repositories, and overly permissive cloud roles.
Amulya Vishwanath, who spent seven years leading product marketing for NVIDIA’s robotics platforms, says robotics is currently in its “Lego era,” with the basic building blocks like actuators, robotic hands, software, and safety standards still being rebuilt.  This view…
Amulya Vishwanath, who spent seven years leading product marketing for NVIDIA’s robotics platforms, says robotics is currently in its “Lego era,” with the basic building blocks like actuators, robotic hands, software, and safety standards still being rebuilt.  This view…
According to Elorian's evaluations, Glimpse outperforms even GPT-6 Astra on scientific chart reasoning and short-form video captioning, with competitive results on other visual reasoning tasks.
Zod is a TypeScript-focused schema validation library that recently released versions 4.5 and 4.6. Key updates include schema compilation for faster data parsing, significant memory usage reductions, and new validation features. The library supports efficient validation processes…
Uber has developed an automated dependency analysis system that uses RPC middleware and production metrics to correlate caller and downstream failures. The approach classifies dependencies as fail-close, fail-open, or unknown and addresses limitations of sampled distributed traci…
A recent InfoQ webinar examined operational challenges in deploying agentic systems. Key points included issues like semantic and embedding drift, which can lead to significant errors. Experts discussed the need for automated code reviews, continuous evaluation of models, and enh…
Counterfeiters are getting better at replicating brands' marks and passing off dupes, known as "superfakes," as genuine items. A startup called Veritas wants to tackle the problem with its own chip that verifies goods.
Identity alone doesn't guarantee a bot will behave responsibly. We are introducing a system to continuously evaluate whether Verified bots honor site preferences, like robots.txt and HTTP 429s, ensuring they remain accountable over time.
Replit CEO Amjad Masad envisions a future of “self-driving companies,” where AI agents handle day-to-day tasks and people focus on higher-level decisions.
Grafana Labs is proposing a familiar reliability engineering approach for one of the less familiar problems in modern software: how to measure whether an AI agent is actually behaving well. By Craig Risi
Discover how to keep software evolvable as systems, technology, and teams shift. This edition explores agentic fitness functions for semantic drift, treating human comprehension as a core design metric, cross-cloud guardrails for regional autonomy, and aligning technical boundari…
The release of Helidon 27 is the first release that follows the Oracle Tip & Tail Model of Library Development by which the Tip adopts the latest Java technology while the Tail provides a more stable and secure baseline. Concurrent with the release of JDK 27, new features in Heli…
Andrew Martin discusses why AI security is fundamentally tied to Kubernetes security. He shares insights into the evolving AI threat landscape, covering non-deterministic agent behavior, GPU supply chain vulnerabilities, shared compute risks, and practical defense strategies - fr…
AWS has introduced two open-source projects for AI agent development: Strands Decider 2B, a small model designed to make decisions within agent workflows, and Strands Box, a sandbox for controlling agent execution. Both projects address different aspects of building agents that u…
This article provides a framework for asking the right architectural questions before an enterprise commits to an mDL provider or library. It shows which components can be abstracted safely, which trust boundaries must remain visible to the enterprise, what cryptographic and inte…
Software supply chain security company Chainguard has announced two beta products for running and testing code written by developers and AI agents. Chainguard Workspaces provides remote development environments based on hardened microVMs, while Chainguard Checks moves continuous …
Microsoft will scale its Maia accelerator family to multi-gigawatt deployments from 2027, making it the primary inference system for its own products. Maia 300 collapses scale-up and scale-out onto one Ethernet fabric and moves KV state between prefill and decode workers without …