Browsing: coding

OpenAI just launched a new research preview called GPT-5.3 Codex-Spark. This model is built for 1 thing: extreme speed. While the standard GPT-5.3 Codex focuses on…

Serving Large Language Models (LLMs) at scale is a massive engineering challenge because of Key-Value (KV) cache management. As models grow in size and reasoning capability,…

What you need to knowNothing’s new Playground tool lets users build simple Android apps using AI, without needing any coding knowledge.Playground creates mini apps based on…

After a week vibe coding apps using Nothing’s Essential Apps Builder, I’m conflicted. I buy into the smartphone maker’s vision for software that adapts to you,…

OpenAI has announced GPT-5.3-Codex, its most advanced code-focused agent to date. According to the company, the new model is 25% faster than GPT-5.2-Codex and has achieved…

In this tutorial, we show how we treat prompts as first-class, versioned artifacts and apply rigorous regression testing to large language model behavior using MLflow. We…

In this tutorial, we build an end-to-end cognitive complexity analysis workflow using complexipy. We start by measuring complexity directly from raw code strings, then scale the…

Anthropic has been buzzing as of late. It recently caused a stock market meltdown with its release of the Claude Cowork tool that tanked the stocks…

Anthropic has launched Claude Opus 4.6, its most capable model to date, focused on long-context reasoning, agentic coding, and high-value knowledge work. The model builds on…

OpenAI has just introduced GPT-5.3-Codex, a new agentic coding model that extends Codex from writing and reviewing code to handling a broad range of work on…