GPT-5.4 is also more reliable, producing 18% fewer errors and 33% fewer false claims than GPT-5.2, according to OpenAI.

OpenAI launches GPT-5.4, calling it its most capable and efficient AI model yet, with AI agents, computer control, improved reasoning, and a 1M-token context.

Building on lessons from an internal agent SDK called “Breadboard”, the agent step is not just another node in a workflow — ...

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Cory Benfield discusses the evolution of ...

In today’s fast-moving business world, managing resources and workflows efficiently has become critical for success. Teams need tools that can streamline operations, improve visibility, and ensure ...

Abstract: Large Language Models (LLMs) have shown promising capabilities in supporting and automating a variety of clearly defined, structured tasks. The engineering of modular plants also follows ...

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...

When the creator of the world's most advanced coding agent speaks, Silicon Valley doesn't just listen — it takes notes. "If you're not reading the Claude Code best practices straight from its creator, ...

AxSTREAM AI can accelerate engineering decisions with workflow-aware intelligence. Read on for a brief market rundown and a few expert takes on how materials innovations are taking shape in 2026 and ...

Positive surgical margins following radical prostatectomy increase the risk of biochemical recurrence and subsequent disease progression. Fluorescence-guided surgery (FGS) using targeted contrast ...