Your daily AI digest for developers — Friday, September 18 2026
The revamped projects feature in Claude Code allows users to run multiple agents under the same roof, with shared memory, goals, and a library of files and artifacts. Each project has 'threads' running different tasks in parallel.
The article describes the process of building a multi-agent system for conducting interrupted time series analysis, turning counterfactual analysis into an AI product.
Agents are becoming the new developer platform, using semantic search with data from tools like Git, Slack, and Jira for context.
The article discusses a framework for reporting self-generated prompt injections in AI models, highlighting potential security risks.
SynthID can cause models to follow harmful instructions they would otherwise refuse, highlighting the impact of AI watermarking on model behavior.
As companies hand off longer and more complex tasks to AI agents, they are running into an oversight problem: Agents can act faster, longer, and at greater volume than humans can realistically review.
Microsoft's AKS engineering team open-sourced TauGrid, packaging several components into one Helm install for Kubernetes clusters with GPU nodes.
PrismML is developing a compact language model that could democratize AI usage by reducing the computational resources required.
The article discusses the materials challenges posed by AI's rapid advancement, emphasizing the importance of semiconductors and data centers.
Matt Pocock explains how he uses AI coding skills and agents to plan and build software, emphasizing the importance of engineering fundamentals.