MIT Technology Review and Microsoft rank 101 agent tasks by practitioner confidence. Report generation tops the index while ...

GitHub secret scanning now extends beyond org-owned repositories: Public Monitoring scans all of GitHub.com in real time, ...

The first proposed catalog of 'configuration smells' reveals widespread issues like context bloat, skill leakage, and conflicting instructions that can make coding agents less reliable and more ...

AI agents waste massive cloud space, so block this bloat early with strict policy checks, illustrated using Terraform and ...

An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...

Visual Studio Code 1.126 adds session-level Copilot cost information, continuing Microsoft's recent focus on helping developers monitor and manage usage-based GitHub Copilot billing.

CVE-2026-12957 in Amazon Q is the third MCP auto-execution vulnerability in three AI coding tools. The pattern reveals a ...

Mozilla researchers revealed a new attack that tricks Claude Code into running hidden commands from seemingly harmless GitHub repositories.

The persistent memory system addresses a real and widely felt pain point in agentic development workflows — one that competitors are also racing to solve.

Amazon Q vulnerability could allow attackers to steal developer cloud credentials by luring them into opening a booby-trapped ...

NVIDIA diffusion language model Nemotron TwoTower achieves 2.42x LLM inference throughput without a full retraining run, ...

A flaw in Hugging Face Transformers could allow malicious AI models to execute code, exposing credentials and highlighting AI supply chain risks.