InfoQ - Large language models - News

AI Code Review at Scale: LinkedIn's Multi-Agent Approach

Sergio De Simone — Sat, 22 Aug 2026 09:00:00 GMT

At LinkedIn's scale, relying solely on human reviewers or simply putting an off-the-shelf AI reviewer in front of GitHub is not an effective way to manage PRs. To address this, LinkedIn engineers built a multi-agent AI code review platform that understands the organizationâ€™s coding context, treats code review as production infrastructure, and minimizes hallucinations and low-signal feedback.

By Sergio De Simone

AWS Releases Aws-Bench to Evaluate Agents on Cloud Tasks

Gianmarco Nalin — Sat, 22 Aug 2026 08:00:00 GMT

AWS has released aws-bench, an open-source benchmark for evaluating AI agents on real AWS tasks such as misconfigurations and infrastructure provisioning. Unlike traditional benchmarks, it uses real resources in disposable AWS accounts, scoring agent performance through automated verifiers.

By Gianmarco Nalin

The Open-Sourcing of DeepSeek Harness Opens the Door to Modular, Unbundled AI Agent Infrastructure

Olimpiu Pop — Thu, 20 Aug 2026 05:05:00 GMT

DeepSeek has released a developer preview of DeepSeek Harness (dsh), an open-source execution runtime for building autonomous AI agents. The software features a micro-kernel architecture with modular plugins for various functional units. The release includes an append-only event logging system for tracking execution activities. Adoption may depend on plugin ecosystem stability and API maintenance.

By Olimpiu Pop

SpaceXAI Launches Grok Bot for Autonomous AI Agents

Daniel Dominguez — Mon, 17 Aug 2026 18:02:00 GMT

SpaceXAI has introduced Grok Bot, a system of persistent AI agents that operate on dedicated cloud computers and can interact with websites, applications, inboxes, and other tools.

By Daniel Dominguez

Meta Open-Sources Muse Glimmer: a 30B Local Agentic Model Optimised for On-Device Execution

Olimpiu Pop — Fri, 14 Aug 2026 05:05:00 GMT

Meta AI Research has introduced Muse Glimmer, a 30-billion-parameter open-weight model under the Apache 2.0 license, designed for local workflows. It enables autonomous agents and complex task execution on consumer GPUs without relying on cloud APIs. The model employs a multi-stage training approach for efficient performance and supports multimodal inputs, enhancing coding and automation tasks.

By Olimpiu Pop

Anthropic's Claude Breaches Sandbox During Model Security Evaluations

Olimpiu Pop — Thu, 13 Aug 2026 10:10:00 GMT

Anthropic conducted an audit of 141006 evaluation runs after OpenAI's sandbox escape disclosure. The review identified three incidents where Claude models accessed the internet due to misconfigurations. These incidents involved unauthorised attacks on live targets. Anthropic has suspended offensive evaluations and plans to enhance security measures and collaborate with external auditors.

By Olimpiu Pop